[test]: regression guard for magi-human SR layout invalidation

Pure logic test (no GPU, no model load, no upstream daVinci-MagiHuman
clone) that asserts MagiHumanSRLatentPreparationStage.forward() clears
batch.magi_static_packed_layout. Catches the f1eeb630 regression that
the existing SR-540p pipeline-parity test missed because that test
bypasses the production stage composition and re-implements the SR
denoise loop with simplified inline helpers, so the cross-stage state
transfer via ForwardBatch is never exercised.

Verified the test fails against HEAD~1 (without the f1eeb630 fix) with:
  AssertionError: assert <sentinel object> is None
and passes against HEAD.

.agents/memory/codebase-map/README.md

@@ -119,7 +119,7 @@ FastVideo-WorldModel/
 ## Build & Test Commands
 
 ```bash
-uv pip install -e .[dev]                          # Editable install
+uv pip install -e ".[dev]"                        # Editable install
 pre-commit run --all-files                        # Lint/format/spell
 pytest tests/                                     # Top-level tests
 pytest fastvideo/tests/ -v                        # Package tests

.agents/scripts/sync-skills.sh

@@ -0,0 +1,96 @@
+#!/usr/bin/env bash
+# Sync .agents/skills/ into .claude/skills/ via per-skill symlinks.
+#
+# Why: Claude Code only scans .claude/skills/ and ~/.claude/skills/ for
+# user-invocable skills (no skillsPath config exists — see
+# https://code.claude.com/docs/en/skills.md). This repo's skills live
+# in .agents/skills/ so they travel with the repo and stay under git.
+# Run this once after cloning (or after adding/removing a skill) to
+# expose them to Claude Code without maintaining a parallel tree.
+#
+# Usage:
+#   .agents/scripts/sync-skills.sh
+#
+# Idempotent and safe to re-run. Prunes stale symlinks whose source
+# has been removed from .agents/skills/. Leaves hand-written
+# .claude/skills/<name>/ directories untouched (only symlinks are
+# managed).
+
+set -euo pipefail
+
+REPO_ROOT="$(git -C "$(dirname "$0")" rev-parse --show-toplevel)"
+SRC_DIR="$REPO_ROOT/.agents/skills"
+DST_DIR="$REPO_ROOT/.claude/skills"
+
+if [[ ! -d "$SRC_DIR" ]]; then
+    echo "Error: $SRC_DIR does not exist." >&2
+    exit 1
+fi
+
+mkdir -p "$DST_DIR"
+
+linked=0
+unchanged=0
+skipped=0
+pruned=0
+
+link_skill() {
+    local name="$1"
+    local src="$SRC_DIR/$name"
+    local dst="$DST_DIR/$name"
+    # Relative target keeps symlinks portable across clones.
+    local rel="../../.agents/skills/$name"
+
+    if [[ -L "$dst" ]]; then
+        if [[ "$(readlink "$dst")" == "$rel" ]]; then
+            unchanged=$((unchanged + 1))
+            return
+        fi
+        rm "$dst"
+    elif [[ -e "$dst" ]]; then
+        echo "Skipped (not a symlink): .claude/skills/$name" >&2
+        skipped=$((skipped + 1))
+        return
+    fi
+
+    ln -s "$rel" "$dst"
+    echo "Linked: .claude/skills/$name -> $rel"
+    linked=$((linked + 1))
+}
+
+prune_stale() {
+    local link="$1"
+    local target
+    target="$(readlink "$link")"
+    case "$target" in
+        ../../.agents/skills/*) ;;
+        *) return ;;
+    esac
+    local name="${target##*/}"
+    if [[ ! -d "$SRC_DIR/$name" ]]; then
+        rm "$link"
+        echo "Pruned stale: .claude/skills/$(basename "$link")"
+        pruned=$((pruned + 1))
+    fi
+}
+
+for src in "$SRC_DIR"/*/; do
+    [[ -d "$src" ]] || continue
+    name="$(basename "$src")"
+    # Only treat directories that actually contain a SKILL.md as skills.
+    [[ -f "$src/SKILL.md" ]] || continue
+    link_skill "$name"
+done
+
+shopt -s nullglob
+for link in "$DST_DIR"/*; do
+    [[ -L "$link" ]] || continue
+    prune_stale "$link"
+done
+shopt -u nullglob
+
+printf "\nSummary: %d linked, %d unchanged, %d pruned" "$linked" "$unchanged" "$pruned"
+if [[ "$skipped" -gt 0 ]]; then
+    printf ", %d skipped (non-symlink collision)" "$skipped"
+fi
+printf "\n"

.agents/skills/index.jsonl

@@ -5,3 +5,6 @@
 {"name": "evaluate-video-quality", "description": "Evaluate generated video quality using available metrics (SSIM, loss trajectory, caption consistency)", "path": "evaluate-video-quality/SKILL.md", "status": "draft", "trust": "low"}
 {"name": "index-related-work", "description": "Ingest a paper or repository into the related work index", "path": "index-related-work/SKILL.md", "status": "draft", "trust": "low"}
 {"name": "search-related-work", "description": "Query the related work index for relevant papers, repos, or comparisons", "path": "search-related-work/SKILL.md", "status": "draft", "trust": "low"}
+{"name": "seed-ssim-references", "description": "Run a new or updated fastvideo/tests/ssim/ test on Modal, pull generated videos, and upload them to FastVideo/ssim-reference-videos so the test has a regression baseline", "path": "seed-ssim-references/SKILL.md", "status": "draft", "trust": "low"}
+{"name": "reseed-ssim-references", "description": "Re-seed (overwrite) HF reference videos for an existing fastvideo/tests/ssim/ test and a single model id on Modal L40S. Always backs up current refs first, regenerates on Modal, pauses for the user to eyeball before-vs-after, then uploads with --force scoped to --model-id. Sister skill to seed-ssim-references; use when intentional code change has invalidated existing refs", "path": "reseed-ssim-references/SKILL.md", "status": "draft", "trust": "low"}
+{"name": "add-model", "description": "Add a new model (or variant) to FastVideo: DiT + configs + pipeline + presets + registry + tests. Walks through FastVideo's single stage-based pipeline architecture with exact file paths and registration hooks.", "path": "add-model/SKILL.md", "status": "draft", "trust": "low"}

.agents/skills/launch-experiment/SKILL.md

@@ -12,7 +12,7 @@ automates the boilerplate of setting environment variables, picking the right
 entrypoint, and applying defaults from the closest example script.
 
 ## Prerequisites
-- The repo is cloned and `fastvideo` is installed (`uv pip install -e .[dev]`).
+- The repo is cloned and `fastvideo` is installed (`uv pip install -e ".[dev]"`).
 - Dataset is preprocessed (see `docs/training/data_preprocess.md`).
 - `WANDB_API_KEY` is set in the environment (or `WANDB_MODE=offline` for local).
 - GPU resources are available (multi-GPU requires NCCL).

.agents/skills/reseed-ssim-references/SKILL.md

@@ -0,0 +1,343 @@
+---
+name: reseed-ssim-references
+description: Re-seed HF reference videos for a single existing SSIM test on Modal L40S. Always backs up current refs locally first, regenerates on Modal, pauses for the user to eyeball before-vs-after quality, then overwrites the targeted `<model_id>` subtree on `FastVideo/ssim-reference-videos` with `--force`. Use when an intentional code change (model port fix, attention backend swap, kernel upgrade, hyperparameter change) has invalidated existing refs and they need to be regenerated. Pairs with `seed-ssim-references`, which is for first-time seeding only.
+---
+
+# Re-seed SSIM Reference Videos
+
+## Purpose
+
+Replace the existing SSIM reference videos for a single `(test_file, model_id)`
+pair on the HF dataset (`FastVideo/ssim-reference-videos`). This is **destructive**
+on HF — the old refs are overwritten — so the skill always:
+
+1. Confirms intent with a one-liner the user has to type.
+2. Downloads the existing refs as a local, timestamped backup.
+3. Regenerates on Modal L40S (same code path that CI uses).
+4. Pauses for a side-by-side eyeball of backup vs new mp4s.
+5. Uploads with `--force`, scoped to the single `--model-id`.
+6. Reminds the user to keep the backup until the PR lands.
+
+Pairs with `seed-ssim-references`, which is the inverse (first-time seeding
+only, refuses to overwrite). Re-seeding is intentionally a separate, more
+ceremonial operation because mistakenly clobbering production refs is much
+harder to recover from than failing closed.
+
+## When to use
+
+- An intentional code change (model port fix, kernel upgrade, attention
+  backend swap, hyperparameter change in the test itself) has shifted the
+  expected SSIM output and the existing refs no longer represent the new
+  ground truth.
+- A test is failing in CI **for the right reason** (the new code is correct,
+  the old refs are stale).
+
+## When not to use
+
+- A test is failing for the **wrong** reason (the port is buggy, not the
+  refs). Fix the port; re-seeding hides the bug.
+- A brand-new test that has no refs on HF yet. Use `seed-ssim-references`.
+- "Just to clean up drift" without a concrete code change to point at. The
+  PR description has to justify *why* refs changed; without a concrete
+  change, there's nothing to write.
+
+## Inputs
+
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| `test_file` | Yes | Path to the SSIM test, e.g. `fastvideo/tests/ssim/test_matrixgame_similarity.py`. Validated against `fastvideo/tests/ssim/test_*_similarity.py`. |
+| `model_id` | Yes | Single model id from the test's `*_MODEL_TO_PARAMS`, e.g. `Matrix-Game-2.0-Diffusers-Base`. Re-seed runs are **per model**. For multi-model tests, invoke the skill once per model. |
+| `intent_rationale` | Yes | One-line explanation of *why* refs are being regenerated (e.g. "Relax FA-2 head_size whitelist to include 80 — matrix_game now uses FLASH_ATTN instead of TORCH_SDPA"). Recorded in the backup directory and reused in the PR description. |
+
+Hardcoded:
+
+- Modal GPU: **L40S** (matches CI; re-seeding from another SKU produces refs
+  that L40S CI cannot match).
+- Quality tier: **`default`**. `full_quality` is a separate, deliberate
+  operation.
+- HF repo: `FastVideo/ssim-reference-videos` (override via
+  `FASTVIDEO_SSIM_REFERENCE_HF_REPO`).
+- Device folder: `L40S_reference_videos`.
+
+## Prerequisites
+
+The user has confirmed:
+
+- `modal` CLI authenticated.
+- `hf` CLI authenticated, **and** `HF_API_KEY` (or `HUGGINGFACE_HUB_TOKEN` /
+  `HF_TOKEN`) exported with **write** access to
+  `FastVideo/ssim-reference-videos`.
+- The current branch's code is the change that motivated the re-seed (i.e.
+  `git rev-parse HEAD` is the commit that intentionally invalidated refs).
+
+Fail fast if any of these are missing.
+
+## Steps
+
+### 1. Validate inputs and confirm intent
+
+- Verify `test_file` exists and matches `fastvideo/tests/ssim/test_*_similarity.py`.
+- Grep the file for `*_MODEL_TO_PARAMS` and assert `model_id` is one of its
+  keys. If the file has only a single hardcoded model, accept that model id
+  as the only valid value.
+- Print the rationale and ask the user to type **`confirm reseed`** (not just
+  `y` — make it deliberate):
+
+  > About to RE-SEED references for model `<model_id>` from test `<test_file>`.
+  > This will OVERWRITE existing refs on
+  > `FastVideo/ssim-reference-videos/reference_videos/default/L40S_reference_videos/<model_id>/`
+  > after backup + Modal regen + eyeball.
+  >
+  > Reason: `<intent_rationale>`
+  > HEAD: `<git rev-parse --short=12 HEAD>`
+  >
+  > Reply `confirm reseed` to proceed, anything else to abort.
+
+  Stop until the user types exactly `confirm reseed`. Anything else aborts
+  with no side effects.
+
+### 2. Back up existing refs
+
+Always required. The backup is the only graceful path back if anything goes
+wrong later.
+
+```bash
+SHORT_COMMIT=$(git rev-parse --short=12 HEAD)
+TIMESTAMP=$(date -u +%Y%m%d_%H%M%S)
+MODEL_SAFE=$(echo "<model_id>" | tr '/' '_')
+BACKUP_DIR="ssim_reseed_backup/${TIMESTAMP}_${SHORT_COMMIT}_${MODEL_SAFE}"
+mkdir -p "$BACKUP_DIR"
+
+hf download \
+    --repo-type dataset FastVideo/ssim-reference-videos \
+    --include "reference_videos/default/L40S_reference_videos/<model_id>/**" \
+    --local-dir "$BACKUP_DIR"
+
+mp4_count=$(find "$BACKUP_DIR" -name "*.mp4" | wc -l)
+echo "Backup mp4 count: $mp4_count"
+[ "$mp4_count" -gt 0 ] || {
+    echo "ERROR: backup is empty for <model_id>. Either the model id is wrong"
+    echo "or there are no existing refs (use seed-ssim-references instead)."
+    exit 1
+}
+
+# Provenance — used in the PR description
+cat > "$BACKUP_DIR/PROVENANCE.txt" <<EOF
+test_file: <test_file>
+model_id: <model_id>
+head_commit: $(git rev-parse HEAD)
+timestamp_utc: $(date -u +%FT%TZ)
+reason: <intent_rationale>
+EOF
+```
+
+If the `hf download` produces zero mp4s, abort — the user has either picked a
+non-existent `model_id` or there are no refs yet (in which case
+`seed-ssim-references` is the right tool).
+
+### 3. Regenerate on Modal L40S
+
+Mirror CI's exact env recipe so the regenerated refs are byte-comparable to
+what CI will produce on the same commit. Two differences from CI:
+
+1. **Pass the same env prefix CI uses** (`IMAGE_VERSION`, `BUILDKITE_*`) — see
+   `.buildkite/pipeline.yml:1-3` and `.buildkite/scripts/pr_test.sh:62-83`.
+   Without this, `ssim_test.py:17-18` resolves a different GHCR image tag
+   (default is `latest`, CI is `py3.12-latest`), and `ssim_test.py:38-46`
+   bakes different values into the image's frozen env block. **Mismatched
+   image or env is the most common source of SSIM drift between reseed and
+   CI runs.**
+2. **Do not pass `--skip-reference-download`**. Letting the test fetch the
+   existing refs and run the full SSIM compare gives "before" SSIM numbers
+   for the PR description, and the test still produces the new mp4s
+   regardless of whether the comparison passes or fails.
+
+```bash
+SUBDIR="${TIMESTAMP}_${SHORT_COMMIT}"
+
+IMAGE_VERSION="py3.12-latest" \
+BUILDKITE_REPO="$(git config --get remote.origin.url)" \
+BUILDKITE_COMMIT="$(git rev-parse HEAD)" \
+BUILDKITE_PULL_REQUEST="${BUILDKITE_PULL_REQUEST:-false}" \
+modal run fastvideo/tests/modal/ssim_test.py \
+    --git-repo="$(git config --get remote.origin.url)" \
+    --git-commit="$(git rev-parse HEAD)" \
+    --hf-api-key="$HF_API_KEY" \
+    --test-files="<test_file>" \
+    --sync-generated-to-volume \
+    --generated-volume-subdir="$SUBDIR" \
+    --no-fail-fast
+```
+
+Capture the printed `modal volume get ...` hint — its `<SUBDIR>` matches
+`$SUBDIR` and is needed for step 4. Capture the SSIM numbers from the test
+output (or from the JSON next to the generated mp4) for the PR description.
+
+### 4. Download generated videos
+
+```bash
+modal volume get --force hf-model-weights \
+    ssim_generated_videos/default/"$SUBDIR"/generated_videos \
+    ./generated_videos_modal/default
+```
+
+After this, the new mp4s live at:
+
+```
+./generated_videos_modal/default/generated_videos/L40S_reference_videos/<model_id>/<backend>/<prompt>.mp4
+```
+
+`--force` is required when `./generated_videos_modal/default` already exists
+from a prior run; safe on the first run too.
+
+### 5. PAUSE — user reviews quality side-by-side
+
+Print the diff and the comparison:
+
+```bash
+echo "=== File list diff (backup vs new) ==="
+diff -u \
+    <(find "$BACKUP_DIR/reference_videos/default/L40S_reference_videos/<model_id>" -name "*.mp4" \
+        | sed "s|$BACKUP_DIR/reference_videos/default/L40S_reference_videos/||" | sort) \
+    <(find ./generated_videos_modal/default/generated_videos/L40S_reference_videos/<model_id> -name "*.mp4" \
+        | sed "s|./generated_videos_modal/default/generated_videos/L40S_reference_videos/||" | sort) \
+    || true
+
+echo
+echo "=== SSIM numbers from this run (paste into PR) ==="
+find ./generated_videos_modal/default/generated_videos/L40S_reference_videos/<model_id> -name "*_ssim.json" -exec cat {} \;
+```
+
+Then stop and tell the user:
+
+> Old refs backed up to `$BACKUP_DIR`.
+> New videos in `./generated_videos_modal/default/generated_videos/L40S_reference_videos/<model_id>/`.
+>
+> Open both in a video player. Confirm the new videos:
+>   1. Look correct (no obvious artifacts, no black/static frames).
+>   2. Are *intentionally* different from the backup in the way described
+>      in `<intent_rationale>` (e.g. slight numerical drift only, not a
+>      different scene / different motion / corrupted output).
+>
+> Reply **`upload`** to overwrite HF, anything else to abort.
+> Aborting leaves the backup and new videos on disk for inspection — nothing
+> on HF changes.
+
+Do not proceed until the user types exactly `upload`. If they abort, leave
+everything on disk and stop here.
+
+### 6. Copy into the local reference layout
+
+Same as `seed-ssim-references` step 5:
+
+```bash
+python fastvideo/tests/ssim/reference_videos_cli.py copy-local \
+    --quality-tier default \
+    --device-folder L40S_reference_videos \
+    --generated-dir ./generated_videos_modal/default/generated_videos/L40S_reference_videos
+```
+
+Result: `fastvideo/tests/ssim/reference_videos/default/L40S_reference_videos/<model_id>/<backend>/<prompt>.mp4`.
+
+### 7. Upload with `--force`, scoped to `--model-id`
+
+The `--force` flag is what makes this skill different from `seed-ssim-references`.
+Always pair it with `--model-id` so a typo cannot accidentally overwrite a
+neighboring model's refs.
+
+```bash
+python fastvideo/tests/ssim/reference_videos_cli.py upload \
+    --quality-tier default \
+    --device-folder L40S_reference_videos \
+    --model-id "<model_id>" \
+    --force
+```
+
+The CLI's overwrite guard refuses without `--force`; with `--force` it
+overwrites only files under
+`reference_videos/default/L40S_reference_videos/<model_id>/`.
+
+### 8. Report success and retention guidance
+
+Print:
+
+- The HF path that was overwritten (`<repo>/reference_videos/default/L40S_reference_videos/<model_id>/`).
+- The local backup directory path.
+- The new SSIM numbers from step 5.
+- This restore command, in case the PR review surfaces a problem after
+  upload:
+
+  ```bash
+  python fastvideo/tests/ssim/reference_videos_cli.py upload \
+      --quality-tier default \
+      --device-folder L40S_reference_videos \
+      --model-id "<model_id>" \
+      --reference-dir "$BACKUP_DIR/reference_videos/default/L40S_reference_videos" \
+      --force
+  ```
+
+- This PR-description checklist (see `fastvideo/tests/ssim/AGENTS.md` →
+  *Updating Reference Videos*):
+  1. Source commit that produced the new refs (HEAD at re-seed time).
+  2. Test command and GPU SKU (`L40S`).
+  3. Before/after SSIM numbers.
+  4. The `<intent_rationale>` from step 1.
+  5. A note that the backup lives at `$BACKUP_DIR` and should be retained
+     until CI on the PR is green.
+
+Do **not** auto-rerun the SSIM test — the user does that as part of the PR.
+
+## Failure modes and how to handle them
+
+- **`HF_API_KEY` unset.** Stop before step 2.
+- **Backup is empty (zero mp4s).** Stop before step 3 — the model id is
+  wrong or the refs don't exist yet (use `seed-ssim-references`).
+- **Modal run fails before generation.** No mp4s on the volume. Don't
+  upload. Investigate the failure (test crash, OOM, partition exhaustion),
+  fix, then retry from step 3. Backup is still intact.
+- **Quality regressed (visual or metric).** User aborts at step 5. Backup
+  retained. New videos retained on disk for inspection. Nothing on HF
+  changed. Either fix the underlying code change or abandon the re-seed.
+- **User confirmed `upload` but later realized the new refs are wrong.**
+  Run the restore command from step 8 with the backup `--reference-dir`.
+  This is exactly why the backup exists.
+- **Multi-model test, only one model is being re-seeded.** Run the skill
+  once per model id. The `--model-id` scope on upload guarantees the others
+  are untouched.
+
+## Design notes (for future skill maintainers)
+
+- Per-`model_id` scope is mandatory. The dataset houses many model subtrees;
+  re-seeding the wrong one is hard to undo without backup.
+- `default` tier only; `full_quality` is a separate, deliberate operation
+  with different params and ~doubled runtime, and isn't what CI gates on.
+- The skill deliberately does **not** pass `--skip-reference-download` to
+  Modal so we get pre-reseed SSIM numbers for the PR. The `seed`-skill
+  passes it because no refs exist yet; for re-seed, refs do exist and
+  exposing the comparison is informative.
+- The two-token confirm (`confirm reseed`, then `upload`) is intentional.
+  Re-seeding is high-blast-radius and should not be one-keystroke.
+- The backup directory is plain mp4s + `PROVENANCE.txt`. No HF metadata is
+  preserved; the restore path uses `reference_videos_cli.py upload
+  --reference-dir` which doesn't need it.
+
+## References
+
+- `.agents/skills/seed-ssim-references/SKILL.md` — the first-time seed
+  skill this one parallels. Read it for the Modal flag rationale shared
+  between the two flows.
+- `fastvideo/tests/ssim/AGENTS.md` — directory rules, including the PR
+  expectations for any reference-video change (rationale, before/after
+  SSIM, source commit/model/backend).
+- `fastvideo/tests/ssim/reference_videos_cli.py` — `copy-local`, `upload`
+  (with `--model-id`, `--force`), `download`. The overwrite guard at
+  `upload_reference_videos` is the safety net this skill leans on.
+- `fastvideo/tests/modal/ssim_test.py` — Modal orchestrator;
+  `--sync-generated-to-volume`, `--generated-volume-subdir`,
+  `--skip-reference-download`, `--no-fail-fast`.
+
+## Changelog
+
+| Date | Change |
+|------|--------|
+| 2026-05-02 | Initial version. Sister skill to `seed-ssim-references`, scoped to single `(test_file, model_id)` re-seeds, with mandatory backup and two-token confirm. |

.agents/skills/seed-ssim-references/SKILL.md

@@ -0,0 +1,376 @@
+---
+name: seed-ssim-references
+description: Seed HF reference artefacts for a single newly-added SSIM test (pixel `.mp4` for `run_text_to_video_similarity_test`-style tests, or latent `.pt` for `run_text_to_latent_similarity_test`-style tests). Runs the test on Modal L40S, downloads the generated artefacts via `modal volume get`, pauses for the user to verify (visual eyeball for mp4, numerics dump for pt), then uploads only that test's files to `FastVideo/ssim-reference-videos`. Use when a new `fastvideo/tests/ssim/test_*_similarity.py` has just been added and has no references on HF yet.
+---
+
+# Seed SSIM Reference Artefacts (mp4 or pt)
+
+## Purpose
+
+A brand-new SSIM test in `fastvideo/tests/ssim/` fails forever until its
+reference artefacts exist on the HF dataset
+(`FastVideo/ssim-reference-videos`). The dataset hosts two kinds of artefacts
+side-by-side per `(model_id, backend, prompt)`:
+
+- **`.mp4`** — pixel ground-truth for tests that call
+  `run_text_to_video_similarity_test` / `run_image_to_video_similarity_test`
+  in `inference_similarity_utils.py`. Compared via SSIM.
+- **`.pt`** — pre-VAE latent bundle (fp16 full latent + fp32 slice +
+  metadata + `slice_spec` + `format_version`) for tests that call
+  `run_text_to_latent_similarity_test` in `latent_similarity_utils.py`.
+  Compared via cosine distance on the slice and the full tensor.
+
+This skill:
+
+1. Detects which artefact type the test produces (pixel vs latent).
+2. Runs the test on Modal's L40S pool to generate the artefacts.
+3. Downloads them to the local repo via `modal volume get`.
+4. Pauses so the user can verify quality:
+   - **mp4**: visual eyeball in a video player.
+   - **pt**: numerics dump (shape, slice stats, NaN/Inf check, metadata).
+5. Uploads only the new test's files to HF, with a guard that refuses to
+   overwrite anything already present.
+
+The skill is run **manually**, once per new test. Before invoking it, the user
+has already sanity-tested the new test locally — it launches `VideoGenerator`
+and writes an artefact without crashing (the missing-reference assertion at
+the end is expected). The skill does not re-test locally; it goes straight
+to Modal L40S (which is what CI uses).
+
+## When to use
+
+- A new `test_*_similarity.py` file has been added in `fastvideo/tests/ssim/`
+  and the HF dataset has no `reference_videos/default/L40S_reference_videos/<model_id>/`
+  subtree for it yet.
+
+## When not to use
+
+- Regular CI runs — once refs exist, `pytest fastvideo/tests/ssim/` downloads
+  them automatically.
+- Re-seeding an existing test. That requires `--force` on the upload step, and
+  is out of scope here; treat as a separate, deliberate operation.
+
+## Inputs
+
+The skill has **one required input**: the path to the new SSIM test file.
+Prompt the user for it if they didn't supply it.
+
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| `test_file` | Yes | e.g. `fastvideo/tests/ssim/test_ltx2_similarity.py`. The skill's first action is to ask for this if missing. |
+
+Everything else is fixed:
+
+- Modal runner GPU: **L40S** (hardcoded in `fastvideo/tests/modal/ssim_test.py`).
+- Device folder: `L40S_reference_videos`.
+- Quality tier: `default` (the tier CI runs). The `full_quality` tier is not
+  seeded by this skill.
+- HF repo: `FastVideo/ssim-reference-videos` (dataset).
+- Multi-model test files: all model ids in `*_MODEL_TO_PARAMS` are seeded
+  together; the Modal run produces one mp4 per (model, prompt, backend) and
+  the upload scopes by `--model-id`, looping if there is more than one.
+
+## Prerequisites
+
+The user has confirmed:
+
+- `modal` CLI authenticated.
+- `HF_API_KEY` (or `HUGGINGFACE_HUB_TOKEN` / `HF_TOKEN`) exported with write
+  access to `FastVideo/ssim-reference-videos`.
+- The test file runs locally end-to-end (generates an mp4; SSIM assertion
+  failure due to missing reference is expected and fine).
+
+Fail fast if the token env var is missing.
+
+## Steps
+
+### 1. Ask for the test file, then detect artefact type
+
+If the user didn't name one, ask: *"Which SSIM test file do you want to seed
+references for? (e.g. `fastvideo/tests/ssim/test_ltx2_similarity.py`)"*.
+
+Validate:
+
+- Path exists and matches `fastvideo/tests/ssim/test_*_similarity.py`.
+- File defines a `*_MODEL_TO_PARAMS` dict — grep it to extract the set of
+  model ids. Those ids drive step 5.
+
+Detect artefact type by inspecting the file's imports / helper call:
+
+- **latent** (`.pt`) — file imports `run_text_to_latent_similarity_test`
+  from `fastvideo.tests.ssim.latent_similarity_utils` (or any other helper
+  that ends with `_latent_similarity_test`).
+- **pixel** (`.mp4`) — file imports
+  `run_text_to_video_similarity_test` / `run_image_to_video_similarity_test`
+  from `fastvideo.tests.ssim.inference_similarity_utils`, OR uses the
+  legacy custom-inline helper pattern (see `test_gamecraft`,
+  `test_longcat`, etc.). Default to pixel when both heuristics fail.
+
+Record `ARTEFACT_TYPE ∈ {pixel, latent}` for use in step 4. Steps 2, 3, 5,
+and 6 are artefact-type-agnostic — `_iter_reference_files`,
+`copy_generated_to_reference`, and `upload_reference_videos` already walk
+both `.mp4` and `.pt` (see `reference_videos_cli.py`).
+
+If either check fails, stop and tell the user what's wrong.
+
+### 2. Run the test on Modal L40S
+
+Pick a subdir name so repeated runs don't collide:
+
+```bash
+SHORT_COMMIT=$(git rev-parse --short=12 HEAD)
+TIMESTAMP=$(date -u +%Y%m%d_%H%M%S)
+SUBDIR="${TIMESTAMP}_${SHORT_COMMIT}"
+```
+
+Then launch the Modal run. The `IMAGE_VERSION` and `BUILDKITE_*` env-prefix
+**must** match what CI exports in `.buildkite/scripts/pr_test.sh`, otherwise
+`fastvideo/tests/modal/ssim_test.py` resolves a different GHCR image tag
+(default is `latest`, CI is `py3.12-latest`) and bakes different values into
+the image's frozen env block (`ssim_test.py:17-18, 38-46`). Mismatched image
+or env produces SSIM drift that doesn't show up until the same commit runs
+in CI.
+
+```bash
+IMAGE_VERSION="py3.12-latest" \
+BUILDKITE_REPO="$(git config --get remote.origin.url)" \
+BUILDKITE_COMMIT="$(git rev-parse HEAD)" \
+BUILDKITE_PULL_REQUEST="${BUILDKITE_PULL_REQUEST:-false}" \
+modal run fastvideo/tests/modal/ssim_test.py \
+    --git-repo="$(git config --get remote.origin.url)" \
+    --git-commit="$(git rev-parse HEAD)" \
+    --hf-api-key="$HF_API_KEY" \
+    --test-files="<test_file>" \
+    --sync-generated-to-volume \
+    --generated-volume-subdir="$SUBDIR" \
+    --skip-reference-download \
+    --no-fail-fast
+```
+
+Env prefix rationale (parity with CI; see `.buildkite/pipeline.yml:1-3` and
+`.buildkite/scripts/pr_test.sh:62-83`):
+- `IMAGE_VERSION=py3.12-latest`: pins the Modal image tag to the same one CI
+  uses. Without this, `ssim_test.py:17` falls back to `latest`, which on
+  GHCR is built from `Dockerfile.python3.10` — different Python, torch, and
+  flash-attn wheel than CI's `py3.12-latest` (`infra-build-image.yml:51-67`,
+  `_template-build-image.yml:65-101`).
+- `BUILDKITE_REPO`/`BUILDKITE_COMMIT`/`BUILDKITE_PULL_REQUEST`: mirror what
+  Buildkite exports. `ssim_test.py:38-46` bakes these into the image's
+  `.env(...)` block; mismatched values can perturb in-container code paths
+  that branch on PR-vs-non-PR. `false` for `BUILDKITE_PULL_REQUEST` matches
+  Buildkite's "non-PR build" sentinel.
+
+Flag rationale:
+- `--skip-reference-download`: no refs exist yet, so conftest must not try to
+  pull them.
+- `--no-fail-fast`: lets the test finish generation before `_assert_similarity`
+  raises `FileNotFoundError: Reference video folder does not exist`. The
+  expected failure is what we want — the mp4 has already been written.
+- `--sync-generated-to-volume` + `--generated-volume-subdir`: copies the
+  generated mp4s to the `hf-model-weights` Modal volume under
+  `ssim_generated_videos/default/<SUBDIR>/generated_videos/` so we can pull
+  them locally.
+
+The Modal run will end with a nonzero exit (expected) and print a
+`modal volume get hf-model-weights ssim_generated_videos/default/<SUBDIR>/generated_videos ./generated_videos_modal/default`
+command. Capture that `<SUBDIR>` — you need it for step 3.
+
+### 3. Download generated videos locally
+
+```bash
+modal volume get --force hf-model-weights \
+    ssim_generated_videos/default/"$SUBDIR"/generated_videos \
+    ./generated_videos_modal/default
+```
+
+`--force` is required when the parent `./generated_videos_modal/default`
+already exists; without it, `modal volume get` errors with `[Errno 21] Is a
+directory`. Safe to pass on the first run too.
+
+After this, the mp4s live at
+`./generated_videos_modal/default/generated_videos/L40S_reference_videos/<model_id>/<backend>/<prompt>.mp4`.
+The extra `generated_videos/` level comes from the volume layout in
+`_sync_generated_videos_to_volume` (`ssim_test.py`) — the command copies
+`<repo>/fastvideo/tests/ssim/generated_videos/<tier>` to
+`ssim_generated_videos/<tier>/<SUBDIR>/generated_videos/`, and `modal volume
+get` preserves that trailing `generated_videos/` segment.
+
+### 4. PAUSE — user reviews quality
+
+Type-aware verification.
+
+**For `ARTEFACT_TYPE = pixel`** — list the downloaded mp4s and ask the user to
+open them in a video player:
+
+> "Generated videos downloaded to `./generated_videos_modal/default/generated_videos/L40S_reference_videos/`. Please open them and confirm the quality looks correct. Reply **`upload`** to continue, or anything else to abort."
+
+**For `ARTEFACT_TYPE = latent`** — `.pt` files are not human-watchable. Print
+a numerics dump for each `.pt` so the user can sanity-check shape, distribution,
+and metadata:
+
+```python
+import torch
+from pathlib import Path
+ROOT = Path("./generated_videos_modal/default/generated_videos/L40S_reference_videos")
+for p in sorted(ROOT.rglob("*.pt")):
+    d = torch.load(p, map_location="cpu", weights_only=False)
+    s = d["expected_slice"]
+    L = d["latent"].float()
+    print(f"=== {p.relative_to(ROOT)} ===")
+    print(f"  format_version: {d['format_version']}")
+    print(f"  shape:          {d['shape']}")
+    print(f"  dtype_original: {d['dtype_original']}")
+    print(f"  slice_spec:     {d['slice_spec']}")
+    print(f"  slice  shape={tuple(s.shape)}  mean={s.mean():+.4f}  std={s.std():.4f}  min={s.min():+.4f}  max={s.max():+.4f}")
+    print(f"  latent shape={tuple(L.shape)}  mean={L.mean():+.4f}  std={L.std():.4f}  min={L.min():+.4f}  max={L.max():+.4f}")
+    print(f"  finite: latent NaN={torch.isnan(L).any().item()} Inf={torch.isinf(L).any().item()}; "
+          f"slice NaN={torch.isnan(s).any().item()} Inf={torch.isinf(s).any().item()}")
+    print(f"  metadata: {d['metadata']}\n")
+```
+
+Sanity criteria:
+- `format_version == 1` (matches `LATENT_REFERENCE_FORMAT_VERSION`).
+- `shape` matches what the model produces (e.g. LTX-2 distilled =
+  `[1, 128, T_lat, H_lat, W_lat]`; Stable Audio Open 1.0 = `[1, 64, 1024]`).
+- `slice_spec.kind` matches a registered kind (`corner_3x3_first_frame`
+  for video, `audio_first_8_timesteps` for audio).
+- No `NaN`/`Inf`. `mean ≈ 0`, `std ≈ 1` (denoised latents stay close to
+  the initial Gaussian distribution; very wide deviations suggest
+  numerical drift).
+- `metadata.prompt` matches the test's prompt.
+
+Then ask:
+
+> "Numerics look right? Reply **`upload`** to continue, or anything else to abort."
+
+Do not proceed until the user explicitly says `upload`. If they abort, leave
+everything on disk so they can inspect further — no cleanup.
+
+### 5. Copy into the local reference layout
+
+Scoped copy — only the new test's artefacts. Single command works for both
+artefact types because `_iter_reference_files` walks `.mp4` and `.pt`:
+
+```bash
+python fastvideo/tests/ssim/reference_videos_cli.py copy-local \
+    --quality-tier default \
+    --device-folder L40S_reference_videos \
+    --generated-dir ./generated_videos_modal/default/generated_videos/L40S_reference_videos
+```
+
+(The `--generated-dir` points at the device-folder root inside the
+downloaded tree; `copy-local` walks all `<model>/<backend>/*.{mp4,pt}`
+underneath it. Since the Modal run was scoped to a single test file via
+`--test-files`, only that test's model(s) are present — so the copy is
+implicitly per-test.)
+
+Result for pixel: `fastvideo/tests/ssim/reference_videos/default/L40S_reference_videos/<model_id>/<backend>/<prompt>.mp4`.
+Result for latent: same path with `.pt` extension.
+
+### 6. Upload to HF — scoped per model_id, with overwrite guard
+
+For each `<model_id>`:
+
+```bash
+python fastvideo/tests/ssim/reference_videos_cli.py upload \
+    --quality-tier default \
+    --device-folder L40S_reference_videos \
+    --model-id "<model_id>"
+```
+
+The upload command:
+
+- Uploads **only** `reference_videos/default/L40S_reference_videos/<model_id>/`.
+- **Refuses** if any file already exists at that path on HF (this is the
+  guard — seeding a new test should never clobber existing refs). To override,
+  the user must re-run with `--force`. If the guard fires, stop and report
+  exactly which files exist; do not silently `--force`.
+
+Reads the HF token from `HF_API_KEY` / `HUGGINGFACE_HUB_TOKEN` / `HF_TOKEN`.
+
+### 7. Report success
+
+List what was uploaded (paths in repo) and remind the user to push any
+related code changes. Do **not** auto-verify by re-running Modal — the user
+can run `pytest fastvideo/tests/ssim/<test_file>` later to confirm end-to-end;
+it will auto-download the refs they just uploaded.
+
+## Failure modes and how to handle them
+
+- **`HF_API_KEY` unset.** Stop before step 2. The Modal run needs it (passed
+  via `--hf-api-key`), and step 6 needs it for upload. If the user
+  ran `hf auth login` instead of exporting an env var, read the cached
+  token via `huggingface_hub.get_token()` and forward it to Modal as
+  `--hf-api-key="$CACHED_TOKEN"`.
+- **Modal run fails before generation.** No artefacts on the volume — nothing
+  to download. Fix the test locally (`pytest fastvideo/tests/ssim/<test_file>`)
+  and retry from step 2.
+- **`./generated_videos_modal/default/L40S_reference_videos/` missing after
+  `modal volume get`.** The run didn't produce artefacts (most likely the
+  test crashed before writing, or `REQUIRED_GPUS` exceeded the partition
+  capacity — see Modal logs).
+- **Latent test crashed with FSDP / inference_mode error
+  (`RuntimeError: Inference tensors do not track version counter`).** The
+  test must pass `init_kwargs_override={"use_fsdp_inference": False}` when
+  `sp_size == 1` — see `test_stable_audio_similarity.py` for the pattern.
+  Fix in the test, push, retry.
+- **Upload guard fires (files already exist).** The test name / model id
+  collides with something already on HF. Verify the user actually wants to
+  replace existing refs; if so, re-run the upload with `--force`. If not,
+  rename the model id in `*_MODEL_TO_PARAMS` and re-seed.
+- **Quality looks wrong in step 4.** Abort. The artefacts stay on disk for
+  inspection. The fix is usually in the test's params (resolution, steps,
+  seed) — edit the test, then re-run the skill.
+  - For latent: also check `slice_spec.kind` matches the latent rank
+    (`corner_3x3_first_frame` requires 5-D, `audio_first_8_timesteps`
+    requires 3-D); a rank/kind mismatch raises in `_extract_expected_slice`.
+
+## Design notes (for future skill maintainers)
+
+- The skill deliberately runs on Modal, **not** locally, because the CI
+  runner is L40S. Seeding from a different GPU SKU produces refs that CI's
+  L40S runs can't match (pixel SSIM drifts across SKUs; latent cosine has
+  tighter cross-SKU bf16 drift but the configured tolerances assume
+  same-SKU seed → same-SKU verify).
+- The skill is default-tier only. `full_quality` refs are seeded by a
+  separate, deliberate operation — they double runtime and aren't what CI
+  gates on.
+- The overwrite guard in `reference_videos_cli.py upload` is default-on
+  specifically because this skill exists. Re-seeding is a distinct operation
+  that requires explicit `--force`.
+- Both artefact types share the same Modal flow: the orchestrator sets
+  `--skip-reference-download` + `--no-fail-fast`, runs pytest, the test's
+  helper writes the artefact (`.mp4` via `imageio` for pixel,
+  `save_latent_reference` → `torch.save` for latent) BEFORE the
+  missing-reference assertion raises. `_sync_generated_videos_to_volume` in
+  `ssim_test.py` does a `shutil.copytree` of the whole `generated_videos/`
+  tree, picking up `.mp4`, `.pt`, and the `*_ssim.json` / `*_latent.json`
+  metric files alongside.
+
+## References
+
+- `fastvideo/tests/modal/ssim_test.py` — Modal orchestrator; see
+  `--sync-generated-to-volume`, `--generated-volume-subdir`,
+  `--skip-reference-download`, `--no-fail-fast`.
+- `fastvideo/tests/ssim/reference_videos_cli.py` — `copy-local`, `upload`
+  (with `--model-id`, `--force`), `download`, `ensure` subcommands.
+  Extension allowlist is `REFERENCE_EXTENSIONS = VIDEO_EXTENSIONS +
+  LATENT_EXTENSIONS` (`.pt`).
+- `fastvideo/tests/ssim/README.md` — reference layout, HF repo conventions.
+- `fastvideo/tests/ssim/inference_similarity_utils.py` — pixel helpers
+  (`run_text_to_video_similarity_test`,
+  `run_image_to_video_similarity_test`, `build_init_kwargs`).
+- `fastvideo/tests/ssim/latent_similarity_utils.py` — latent helper
+  (`run_text_to_latent_similarity_test`), slice spec dispatch
+  (`_extract_expected_slice`), reference schema
+  (`save_latent_reference` / `load_latent_reference`),
+  `LATENT_REFERENCE_FORMAT_VERSION`.
+
+## Changelog
+
+| Date | Change |
+|------|--------|
+| 2026-04-17 | Initial version (Modal sync-to-volume flow). |
+| 2026-04-21 | Rewrite: single-test scope, explicit user-review pause, per-`model_id` upload, HF overwrite guard. Dropped `scripts/seed_ssim.sh`. |
+| 2026-04-21 | Post-first-run fixes: `modal volume get` needs `--force` when parent exists; download tree has an extra `generated_videos/` level so `--generated-dir` must reflect it. |
+| 2026-05-01 | Latent (`*.pt`) artefact support: artefact-type detection in step 1, type-aware verification (visual eyeball for mp4, numerics dump for pt) in step 4, FSDP+inference_mode failure-mode added, design notes for the unified Modal flow. Triggered by PR #1253 (LTX-2 latent migration + Stable Audio latent test). |

.buildkite/performance-benchmarks/tests/wan-t2v-1.3b.json

@@ -29,8 +29,8 @@
     "Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of a bustling street food market. The scene captures a mix of humor and authenticity. Mid-shot framing, vibrant lighting."
   ],
   "run_config": {
-    "num_warmup_runs": 1,
-    "num_measurement_runs": 3,
+    "num_warmup_runs": 2,
+    "num_measurement_runs": 5,
     "required_gpus": 2
   },
   "thresholds": {

.buildkite/pipeline.yml

@@ -2,20 +2,218 @@ env:
   IMAGE_VERSION: "py3.12-latest"
   BUILDKITE_CLEAN_CHECKOUT: true
 
+notify:
+  - github_commit_status:
+      context: "fastcheck-passed"
+    if: build.env("TEST_SCOPE") == "fastcheck" || build.env("TEST_SCOPE") == null
+  - github_commit_status:
+      context: "full-suite-passed"
+    if: build.env("TEST_SCOPE") == "full"
+  - github_commit_status:
+      context: "direct-test-completed"
+    if: build.env("TEST_SCOPE") == "direct"
+
 steps:
-  - label: "pre-commit"
-    command: ".buildkite/scripts/pre_commit.sh"
-    agents:
-      queue: "default"
+  # ============================================================
+  # Direct test: triggered by /test <name> slash command.
+  # Labels match fastcheck/full-suite counterparts so the GitHub
+  # check status overwrites the original failed check.
+  # Only ONE step executes per build (gated by TEST_TYPE).
+  # ============================================================
 
-  - wait
+  # --- Fastcheck-scope direct tests ---
+    - label: ":microscope: Encoder Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "encoder"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":microscope: VAE Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "vae"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":microscope: Transformer Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "transformer"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":microscope: Kernel Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "kernel_tests"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":microscope: Unit Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "unit_test"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
 
-  - label: "Trigger Tests"
-    plugins:
-      - monorepo-diff#v1.4.0:
-          diff: 'git fetch origin "$BUILDKITE_PULL_REQUEST_BASE_BRANCH" && git diff --name-only origin/"$BUILDKITE_PULL_REQUEST_BASE_BRANCH"...HEAD'
-          watch:
-            - path: 
+  # --- Full-suite-scope direct tests ---
+    - label: ":bar_chart: SSIM Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "ssim"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+          - exit_status: 1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: LoRA Inference Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "inference_lora"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: Training Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "training"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: Distillation DMD Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "distillation_dmd"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: Self-Forcing Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "self_forcing"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: LoRA Training Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "training_lora"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+          - exit_status: 1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: Training Tests VSA"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "training_vsa"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+          - exit_status: 1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: Inference Tests VMoBA"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "inference_vmoba"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: Performance Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "performance"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+    - label: ":test_tube: API Server Tests"
+      if: build.env("TEST_SCOPE") == "direct" && build.env("TEST_TYPE") == "api_server"
+      command: "timeout 90m .buildkite/scripts/pr_test.sh"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      agents:
+        queue: "default"
+
+  # ============================================================
+  # Fastcheck: Runs on every PR (~10-15 min parallel)
+  # Core component validation: encoders, VAEs, transformers,
+  # CUDA kernels, and unit tests.
+  # ============================================================
+    - label: "Trigger Fastcheck"
+      if: build.env("TEST_SCOPE") == "fastcheck" || build.env("TEST_SCOPE") == null
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      plugins:
+        - monorepo-diff#v1.4.0:
+            diff: 'git fetch origin "${BUILDKITE_PULL_REQUEST_BASE_BRANCH:-main}" && git diff --name-only "origin/${BUILDKITE_PULL_REQUEST_BASE_BRANCH:-main}...HEAD"'
+            watch:
+            - path:
                 - "fastvideo/models/encoders/**"
                 - "fastvideo/models/loader/**"
                 - "fastvideo/tests/encoders/**"
@@ -23,7 +221,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 20m .buildkite/scripts/pr_test.sh"
-                label: "Encoder Tests"
+                label: ":microscope: Encoder Tests"
                 env:
                   - TEST_TYPE=encoder
                 agents:
@@ -36,7 +234,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 20m .buildkite/scripts/pr_test.sh"
-                label: "VAE Tests"
+                label: ":microscope: VAE Tests"
                 env:
                   - TEST_TYPE=vae
                 agents:
@@ -51,20 +249,68 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Transformer Tests"
+                label: ":microscope: Transformer Tests"
                 env:
                   - TEST_TYPE=transformer
                 agents:
                   queue: "default"
-            - path: 
+            - path:
+                - "fastvideo-kernel/**"
+                - "pyproject.toml"
+                - "docker/Dockerfile.python3.12"
+              config:
+                command: "timeout 15m .buildkite/scripts/pr_test.sh"
+                label: ":microscope: Kernel Tests"
+                env:
+                  - TEST_TYPE=kernel_tests
+                agents:
+                  queue: "default"
+            - path:
+                - "fastvideo/**"
+                - ".buildkite/**"
+                - ".github/**"
+                - "pyproject.toml"
+                - "docker/Dockerfile.python3.12"
+              config:
+                command: "timeout 15m .buildkite/scripts/pr_test.sh"
+                label: ":microscope: Unit Tests"
+                env:
+                  - TEST_TYPE=unit_test
+                agents:
+                  queue: "default"
+
+  # ============================================================
+  # Full Suite: Runs when TEST_SCOPE=full
+  # Triggered by adding the 'ready' label (via ci-trigger-full-suite.yml)
+  # or on-demand via /test full slash command.
+  # Includes integration tests, SSIM regression, training pipelines,
+  # and performance benchmarks.
+  # ============================================================
+    - label: "Trigger Full Suite"
+      if: build.env("TEST_SCOPE") == "full"
+      retry:
+        automatic:
+          - exit_status: 128
+            limit: 3
+          - exit_status: -1
+            limit: 2
+      plugins:
+        - monorepo-diff#v1.4.0:
+            diff: 'git fetch origin "${BUILDKITE_PULL_REQUEST_BASE_BRANCH:-main}" && git diff --name-only "origin/${BUILDKITE_PULL_REQUEST_BASE_BRANCH:-main}...HEAD"'
+            watch:
+            - path:
                 - "fastvideo/**/*.py"
                 - "pyproject.toml"
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 90m .buildkite/scripts/pr_test.sh"
-                label: "SSIM Tests"
+                label: ":bar_chart: SSIM Tests"
                 env:
                   - TEST_TYPE=ssim
+                retry:
+                  automatic:
+                    - exit_status: 1
+                      limit: 2
                 agents:
                   queue: "default"
             - path:
@@ -77,7 +323,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 20m .buildkite/scripts/pr_test.sh"
-                label: "LoRA Inference Tests"
+                label: ":test_tube: LoRA Inference Tests"
                 env:
                   - TEST_TYPE=inference_lora
                 agents:
@@ -88,7 +334,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Training Tests"
+                label: ":test_tube: Training Tests"
                 env:
                   - TEST_TYPE=training
                 agents:
@@ -99,7 +345,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Distillation DMDTests"
+                label: ":test_tube: Distillation DMD Tests"
                 env:
                   - TEST_TYPE=distillation_dmd
                 agents:
@@ -111,7 +357,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Self-Forcing Tests"
+                label: ":test_tube: Self-Forcing Tests"
                 env:
                   - TEST_TYPE=self_forcing
                 agents:
@@ -122,9 +368,13 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "LoRA Training Tests"
+                label: ":test_tube: LoRA Training Tests"
                 env:
                   - TEST_TYPE=training_lora
+                retry:
+                  automatic:
+                    - exit_status: 1
+                      limit: 2
                 agents:
                   queue: "default"
             - path:
@@ -134,20 +384,15 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Training Tests VSA"
+                label: ":test_tube: Training Tests VSA"
                 env:
                   - TEST_TYPE=training_vsa
+                retry:
+                  automatic:
+                    - exit_status: 1
+                      limit: 2
                 agents:
                   queue: "default"
-            - path:
-                - "fastvideo-kernel/**"
-                - "pyproject.toml"
-                - "docker/Dockerfile.python3.12"
-              config:
-                command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Kernel Tests"
-                env:
-                  - TEST_TYPE=kernel_tests
             - path:
                 - "fastvideo-kernel/**"
                 - "fastvideo/attention/backends/vmoba.py"
@@ -155,20 +400,9 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Inference Tests VMoBA"
-                env:  
-                  - TEST_TYPE=inference_vmoba
-                agents:
-                  queue: "default"
-            - path:
-                - "fastvideo/**"
-                - "pyproject.toml"
-                - "docker/Dockerfile.python3.12"
-              config:
-                command: "timeout 15m .buildkite/scripts/pr_test.sh"
-                label: "Unit Tests"
+                label: ":test_tube: Inference Tests VMoBA"
                 env:
-                  - TEST_TYPE=unit_test
+                  - TEST_TYPE=inference_vmoba
                 agents:
                   queue: "default"
             - path:
@@ -184,7 +418,7 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 30m .buildkite/scripts/pr_test.sh"
-                label: "Performance Tests"
+                label: ":test_tube: Performance Tests"
                 env:
                   - TEST_TYPE=performance
                 agents:
@@ -197,19 +431,8 @@ steps:
                 - "docker/Dockerfile.python3.12"
               config:
                 command: "timeout 30m .buildkite/scripts/pr_test.sh"
-                label: "API Server Tests"
+                label: ":test_tube: API Server Tests"
                 env:
                   - TEST_TYPE=api_server
                 agents:
                   queue: "default"
-            # - path:
-            #     - "scripts/lora_extraction/**"
-            #     - "pyproject.toml"
-            #     - "docker/Dockerfile.python3.12"
-            #   config:
-            #     command: "timeout 90m .buildkite/scripts/pr_test.sh"
-            #     label: "LoRA Extraction Tests"
-            #     env:
-            #       - TEST_TYPE=lora_extraction
-            #     agents:
-            #       queue: "default"

.buildkite/scripts/pr_test.sh

@@ -15,8 +15,21 @@ log "Project root: $PROJECT_ROOT"
 # Install Modal if not available
 if ! python3 -m modal --version &> /dev/null; then
     log "Modal not found, installing..."
-    python3 -m pip install modal
-    
+    if ! command -v uv &> /dev/null; then
+        log "uv not found, bootstrapping..."
+        if ! curl -LsSf https://astral.sh/uv/install.sh | sh; then
+            log "Error: Failed to bootstrap uv via astral.sh installer."
+            exit 1
+        fi
+        export PATH="$HOME/.local/bin:$PATH"
+        if ! command -v uv &> /dev/null; then
+            log "Error: uv still not on PATH after bootstrap."
+            exit 1
+        fi
+    fi
+    # --break-system-packages preserves prior `pip install --user` semantics on PEP 668 agents.
+    uv pip install --system --break-system-packages modal
+
     # Verify installation
     if ! python3 -m modal --version &> /dev/null; then
         log "Error: Failed to install modal. Please install it manually."
@@ -59,7 +72,76 @@ if [ -z "${TEST_TYPE:-}" ]; then
 fi
 log "Test type: $TEST_TYPE"
 
-MODAL_ENV="BUILDKITE_REPO=$BUILDKITE_REPO BUILDKITE_COMMIT=$BUILDKITE_COMMIT BUILDKITE_PULL_REQUEST=$BUILDKITE_PULL_REQUEST IMAGE_VERSION=$IMAGE_VERSION"
+EFFECTIVE_PR=${BUILDKITE_PULL_REQUEST:-false}
+if [ "$EFFECTIVE_PR" = "false" ] && [ -n "${PR_NUMBER:-}" ]; then
+    EFFECTIVE_PR=$PR_NUMBER
+fi
+MODAL_ENV="BUILDKITE_REPO=$BUILDKITE_REPO BUILDKITE_COMMIT=$BUILDKITE_COMMIT BUILDKITE_PULL_REQUEST=$EFFECTIVE_PR BUILDKITE_BRANCH=${BUILDKITE_BRANCH:-} TEST_SCOPE=${TEST_SCOPE:-} IMAGE_VERSION=$IMAGE_VERSION"
+
+POST_RUN_HOOK=""
+
+upload_performance_artifacts() {
+    SHORT_SHA=${BUILDKITE_COMMIT:0:7}
+    LOCAL_DIR="downloaded_reports"
+
+    _download_reports() {
+        log "Downloading perf_reports/ from Modal Volume..."
+        mkdir -p "$LOCAL_DIR"
+        if ! modal volume get hf-model-weights "perf_reports/" "$LOCAL_DIR"; then
+            log "Error: Failed to download perf_reports/ from Modal Volume."
+            return 1
+        fi
+    }
+
+    _upload_dashboard() {
+        local target
+        target=$(find "$LOCAL_DIR" -name "dashboard_${SHORT_SHA}_*" | head -n 1)
+        log "TARGET dashboard: '$target'"
+
+        if [ -n "$target" ]; then
+            log "Found dashboard: $target. Uploading to Buildkite..."
+            buildkite-agent artifact upload "$target"
+            buildkite-agent annotate --style info --context "perf-dashboard" < "$target"
+        else
+            log "Warning: Could not find a dashboard file matching $SHORT_SHA"
+        fi
+    }
+
+    _upload_perf_summary() {
+        local target
+        target=$(find "$LOCAL_DIR" -name "perf_${SHORT_SHA}_*" | head -n 1)
+        log "TARGET perf summary: '$target'"
+
+        if [ -n "$target" ]; then
+            log "Found perf summary: $target. Uploading to Buildkite..."
+            buildkite-agent artifact upload "$target"
+            buildkite-agent annotate --style info --context "perf-summary" < "$target"
+        else
+            log "Warning: Could not find a perf summary file matching $SHORT_SHA"
+        fi
+    }
+
+    _cleanup_modal_volume() {
+        log "Cleaning up perf_reports/ from Modal Volume..."
+        if modal volume rm hf-model-weights "perf_reports/" --recursive; then
+            log "Successfully deleted perf_reports/ from Modal Volume."
+        else
+            log "Warning: Failed to delete perf_reports/ from Modal Volume. Manual cleanup may be required."
+        fi
+    }
+
+    _cleanup_local() {
+        log "Cleaning up local download directory..."
+        rm -rf "$LOCAL_DIR"
+    }
+
+    # --- Main flow ---
+    _download_reports || { _cleanup_local; return 1; }
+    _upload_dashboard
+    _upload_perf_summary
+    _cleanup_modal_volume
+    _cleanup_local
+}
 
 case "$TEST_TYPE" in
     "encoder")
@@ -120,8 +202,9 @@ case "$TEST_TYPE" in
         MODAL_COMMAND="$MODAL_ENV HF_API_KEY=$HF_API_KEY python3 -m modal run $MODAL_TEST_FILE::run_lora_extraction_tests"
         ;;
     "performance")
-        log "Running performance tests..."
+        log "Running performance tests on Modal..."
         MODAL_COMMAND="$MODAL_ENV HF_API_KEY=$HF_API_KEY python3 -m modal run $MODAL_TEST_FILE::run_performance_tests"
+        POST_RUN_HOOK="upload_performance_artifacts"
         ;;
     "api_server")
         log "Running API server integration tests..."
@@ -143,5 +226,10 @@ else
     log "Error: Modal test failed with exit code: $TEST_EXIT_CODE"
 fi
 
+if [ -n "$POST_RUN_HOOK" ]; then
+    log "Executing post-run hook: $POST_RUN_HOOK"
+    "$POST_RUN_HOOK"
+fi
+
 log "=== Test execution completed with exit code: $TEST_EXIT_CODE ==="
 exit $TEST_EXIT_CODE

.buildkite/scripts/pre_commit.sh

@@ -13,8 +13,21 @@ log "Project root: $PROJECT_ROOT"
 
 if ! python3 -m pre_commit --version &> /dev/null; then
     log "pre-commit not found, installing..."
-    python3 -m pip install --user pre-commit==4.0.1
-    
+    if ! command -v uv &> /dev/null; then
+        log "uv not found, bootstrapping..."
+        if ! curl -LsSf https://astral.sh/uv/install.sh | sh; then
+            log "Error: Failed to bootstrap uv via astral.sh installer."
+            exit 1
+        fi
+        export PATH="$HOME/.local/bin:$PATH"
+        if ! command -v uv &> /dev/null; then
+            log "Error: uv still not on PATH after bootstrap."
+            exit 1
+        fi
+    fi
+    # --break-system-packages preserves prior `pip install --user` semantics on PEP 668 agents.
+    uv pip install --system --break-system-packages pre-commit==4.0.1
+
     if ! python3 -m pre_commit --version &> /dev/null; then
         log "Error: Failed to install pre-commit."
         exit 1

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +1,22 @@
+<!--
+PR TITLE: Must start with a type tag, e.g.:
+  [feat] Add new model       [bugfix] Fix VAE tiling      [refactor] Restructure pipeline
+  [perf] Optimize kernel     [ci] Update tests             [docs] Add guide
+  [misc] Cleanup configs     [new-model] Port Flux2
+
+MERGE WORKFLOW:
+  1. Ensure pre-commit passes and you have at least 1 approval
+  2. Comment /merge (or add the "ready" label) to enter the Merge Queue
+  3. Full Test Suite runs automatically on a staging branch → auto-merge on success
+
+ON-DEMAND TESTING (write access required):
+  /test full       — Full Test Suite        /test ssim        — SSIM regression
+  /test training   — Training pipeline      /test encoder     — Encoder tests
+  /test transformer — Transformer tests     /test vae         — VAE tests
+  /test kernel     — CUDA kernel tests      /test unit        — Unit tests
+  See docs/contributing/pull_requests.md for all 17 test commands
+-->
+
 ## Purpose
 
 <!-- What does this PR do? Link the related issue if applicable. -->

.github/mergify.yml

@@ -0,0 +1,316 @@
+merge_protections:
+  - name: PR merge requirements
+    if:
+      - base = main
+    success_conditions:
+      - "title~=(?i)^\\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model)\\]"
+      - "#approved-reviews-by>=1"
+      - check-success~=pre-commit
+      - check-success=fastcheck-passed
+      - check-success=full-suite-passed
+
+pull_request_rules:
+
+  # ============================================================
+  # Type labels (from PR title prefix)
+  # ============================================================
+
+  - name: "label type: feat"
+    conditions:
+      - "title~=(?i)^\\[(feat|feature)\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: feat"]
+
+  - name: "label type: bugfix"
+    conditions:
+      - "title~=(?i)^\\[(bug)?fix\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: bugfix"]
+
+  - name: "label type: refactor"
+    conditions:
+      - "title~=(?i)^\\[refactor\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: refactor"]
+
+  - name: "label type: perf"
+    conditions:
+      - "title~=(?i)^\\[perf\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: perf"]
+
+  - name: "label type: ci"
+    conditions:
+      - "title~=(?i)^\\[ci\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: ci"]
+
+  - name: "label type: docs"
+    conditions:
+      - "title~=(?i)^\\[(doc|docs)\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: docs"]
+
+  - name: "label type: misc"
+    conditions:
+      - "title~=(?i)^\\[(misc|chore)\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: misc"]
+
+  - name: "label type: new-model"
+    conditions:
+      - "title~=(?i)^\\[new.?model\\]"
+      - -closed
+    actions:
+      label:
+        add: ["type: new-model"]
+
+  # ============================================================
+  # Scope labels (from changed files)
+  # ============================================================
+
+  - name: "label scope: training"
+    conditions:
+      - or:
+          - files~=^fastvideo/train/
+          - files~=^fastvideo/training/
+          - files~=^fastvideo/distillation/
+          - files~=^examples/train/
+          - files~=^examples/training/
+          - files~=^examples/distill/
+      - -closed
+    actions:
+      label:
+        add: ["scope: training"]
+
+  - name: "label scope: inference"
+    conditions:
+      - or:
+          - files~=^fastvideo/pipelines/basic/
+          - files~=^fastvideo/pipelines/stages/
+          - files~=^fastvideo/pipelines/samplers/
+          - files~=^fastvideo/entrypoints/
+          - files~=^fastvideo/worker/
+          - files~=^fastvideo/api/sampling_param
+          - files~=^fastvideo/configs/pipelines/
+          - files~=^examples/inference/
+      - -closed
+    actions:
+      label:
+        add: ["scope: inference"]
+
+  - name: "label scope: attention"
+    conditions:
+      - files~=^fastvideo/attention/
+      - -closed
+    actions:
+      label:
+        add: ["scope: attention"]
+
+  - name: "label scope: kernel"
+    conditions:
+      - or:
+          - files~=^fastvideo-kernel/
+          - files~=^csrc/
+      - -closed
+    actions:
+      label:
+        add: ["scope: kernel"]
+
+  - name: "label scope: data"
+    conditions:
+      - or:
+          - files~=^fastvideo/dataset/
+          - files~=^fastvideo/pipelines/preprocess/
+          - files~=^examples/preprocessing/
+      - -closed
+    actions:
+      label:
+        add: ["scope: data"]
+
+  - name: "label scope: infra"
+    conditions:
+      - or:
+          - files~=^\.github/
+          - files~=^\.buildkite/
+          - files~=^fastvideo/tests/
+          - files~=^docker/
+      - -closed
+    actions:
+      label:
+        add: ["scope: infra"]
+
+  - name: "label scope: distributed"
+    conditions:
+      - files~=^fastvideo/distributed/
+      - -closed
+    actions:
+      label:
+        add: ["scope: distributed"]
+
+  - name: "label scope: docs"
+    conditions:
+      - files~=^docs/
+      - -closed
+    actions:
+      label:
+        add: ["scope: docs"]
+
+  - name: "label scope: ui"
+    conditions:
+      - files~=^ui/
+      - -closed
+    actions:
+      label:
+        add: ["scope: ui"]
+
+  - name: "label scope: model"
+    conditions:
+      - or:
+          - files~=^fastvideo/models/
+          - files~=^fastvideo/layers/
+          - files~=^fastvideo/configs/models/
+      - -closed
+    actions:
+      label:
+        add: ["scope: model"]
+
+  # ============================================================
+  # Pre-commit failure help comment
+  # ============================================================
+
+  - name: comment on pre-commit failure
+    conditions:
+      - check-failure~=pre-commit
+      - -closed
+    actions:
+      comment:
+        message: |
+          ## Pre-commit checks failed
+
+          Hi @{{author}}, the pre-commit checks have failed. To fix them locally:
+
+          ```bash
+          # Install pre-commit if you haven't already
+          uv pip install pre-commit
+          pre-commit install
+
+          # Run all checks and auto-fix what's possible
+          pre-commit run --all-files
+          ```
+
+          Common fixes:
+          - **yapf**: `yapf -i <file>` (formatting)
+          - **ruff**: `ruff check --fix <file>` (linting)
+          - **codespell**: `codespell --write-changes <file>` (spelling)
+
+          After fixing, commit and push the changes. The checks will re-run automatically.
+
+          For future commits, `pre-commit` will run automatically on changed files before each commit.
+
+
+  # ============================================================
+  # Merge conflict detection
+  # ============================================================
+
+  - name: label conflicting PRs
+    conditions:
+      - conflict
+      - -closed
+      - label!=stale
+    actions:
+      label:
+        add: [needs-rebase]
+      comment:
+        message: |
+          This PR has merge conflicts with the base branch. Please rebase:
+
+          ```bash
+          git fetch origin main
+          git rebase origin/main
+          # Resolve any conflicts, then:
+          git push --force-with-lease
+          ```
+
+  - name: remove conflict label when resolved
+    conditions:
+      - -conflict
+      - -closed
+      - label=needs-rebase
+    actions:
+      label:
+        remove: [needs-rebase]
+
+  # ============================================================
+  # Auto-merge and auto-rebase
+  # ============================================================
+
+  - name: auto-merge when ready and all checks pass
+    conditions:
+      - label=ready
+      - "title~=(?i)^\\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model)\\]"
+      - "#approved-reviews-by>=1"
+      - check-success~=pre-commit
+      - check-success=fastcheck-passed
+      - check-success=full-suite-passed
+      - -conflict
+      - -closed
+      - -draft
+    actions:
+      merge:
+        method: squash
+
+  - name: auto-update when ready
+    conditions:
+      - label=ready
+      - "#approved-reviews-by>=1"
+      - -conflict
+      - -closed
+      - -draft
+    actions:
+      update: {}
+
+  # ============================================================
+  # PR title format help
+  # ============================================================
+
+  - name: comment on invalid PR title format
+    conditions:
+      - -closed
+      - -draft
+      - "-title~=(?i)^\\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model)\\]"
+    actions:
+      comment:
+        message: |
+          ## ⚠️ PR title format required
+
+          Your PR title must start with a type tag in brackets. Examples:
+          - `[feat] Add new model support`
+          - `[bugfix] Fix VAE tiling corruption`
+          - `[refactor] Restructure training pipeline`
+          - `[perf] Optimize attention kernel`
+          - `[ci] Update test infrastructure`
+          - `[docs] Add inference guide`
+          - `[misc] Clean up configs`
+          - `[new-model] Port Flux2 to FastVideo`
+
+          Valid tags: `feat`, `feature`, `bugfix`, `fix`, `refactor`, `perf`, `ci`, `doc`, `docs`, `misc`, `chore`, `kernel`, `new-model`
+
+          Please update your PR title and the merge protection check will pass automatically.
+
+merge_protections_settings:
+  reporting_method: check-runs

.github/scripts/runpod_api.py

@@ -1,249 +0,0 @@
-import argparse
-import json
-import os
-import subprocess
-import sys
-import time
-
-import requests
-
-
-def parse_arguments():
-    """Parse command line arguments"""
-    parser = argparse.ArgumentParser(description='Run tests on RunPod GPU')
-    parser.add_argument('--gpu-type', type=str, help='GPU type to use')
-    parser.add_argument('--gpu-count',
-                        type=int,
-                        help='Number of GPUs to use',
-                        default=1)
-    parser.add_argument('--test-command', type=str, help='Test command to run')
-    parser.add_argument('--disk-size',
-                        type=int,
-                        default=20,
-                        help='Container disk size in GB (default: 20)')
-    parser.add_argument('--volume-size',
-                        type=int,
-                        default=20,
-                        help='Persistent volume size in GB (default: 20)')
-    parser.add_argument(
-        '--image',
-        type=str,
-        required=True,
-        help='Docker image to use')
-    return parser.parse_args()
-
-
-args = parse_arguments()
-API_KEY = os.environ['RUNPOD_API_KEY']
-RUN_ID = os.environ['GITHUB_RUN_ID']
-JOB_ID = os.environ['JOB_ID']
-PODS_API = "https://rest.runpod.io/v1/pods"
-HEADERS = {
-    "Content-Type": "application/json",
-    "Authorization": f"Bearer {API_KEY}"
-}
-
-
-def create_pod():
-    """Create a RunPod instance"""
-    # Ensure image name is lowercase (Docker requirement)
-    image_name = args.image.lower()
-    print(f"Using specified image: {image_name}")
-
-    docker_start_cmd = [
-        "bash", 
-        "-c", 
-        "apt update;DEBIAN_FRONTEND=noninteractive apt-get install openssh-server -y;mkdir -p ~/.ssh;cd $_;chmod 700 ~/.ssh;echo \"$PUBLIC_KEY\" >> authorized_keys;chmod 700 authorized_keys;service ssh start;sleep infinity"
-    ]
-    
-    print(f"Creating RunPod instance with GPU: {args.gpu_type}...")
-    payload = {
-        "name": f"fastvideo-{JOB_ID}-{RUN_ID}",
-        "containerDiskInGb": args.disk_size,
-        "volumeInGb": args.volume_size,
-        "gpuTypeIds": [args.gpu_type],
-        "gpuCount": args.gpu_count,
-        "imageName": image_name,
-        "allowedCudaVersions": ["12.4"],
-        "dockerStartCmd": docker_start_cmd
-    }
-
-    response = requests.post(PODS_API, headers=HEADERS, json=payload)
-    response_data = response.json()
-    print(f"Response: {json.dumps(response_data, indent=2)}")
-
-    return response_data["id"]
-
-
-def wait_for_pod(pod_id):
-    """Wait for pod to be in RUNNING state and fully ready with SSH access"""
-    print("Waiting for RunPod to be ready...")
-
-    # First wait for RUNNING status
-    max_attempts = 10
-    attempts = 0
-    while attempts < max_attempts:
-        response = requests.get(f"{PODS_API}/{pod_id}", headers=HEADERS)
-        pod_data = response.json()
-        status = pod_data["desiredStatus"]
-
-        if status == "RUNNING":
-            print("RunPod is running! Now waiting for ports to be assigned...")
-            break
-
-        print(
-            f"Current status: {status}, waiting... (attempt {attempts+1}/{max_attempts})"
-        )
-        time.sleep(2)
-        attempts += 1
-
-    if attempts >= max_attempts:
-        raise TimeoutError(
-            "Timed out waiting for RunPod to reach RUNNING state")
-
-    # Wait for ports to be assigned
-    max_attempts = 50
-    attempts = 0
-    while attempts < max_attempts:
-        response = requests.get(f"{PODS_API}/{pod_id}", headers=HEADERS)
-        pod_data = response.json()
-        port_mappings = pod_data.get("portMappings")
-
-        if (port_mappings is not None and "22" in port_mappings
-                and pod_data.get("publicIp", "") != ""):
-            print("RunPod is ready with SSH access!")
-            print(f"SSH IP: {pod_data['publicIp']}")
-            print(f"SSH Port: {port_mappings['22']}")
-            break
-
-        print(
-            f"Waiting for SSH port and public IP to be available... (attempt {attempts+1}/{max_attempts})"
-        )
-        time.sleep(20)
-        attempts += 1
-
-    if attempts >= max_attempts:
-        raise TimeoutError("Timed out waiting for RunPod SSH access")
-
-
-def execute_command(pod_id):
-    """Execute command on the pod via SSH using system SSH client"""
-    print(f"Running command: {args.test_command}")
-
-    response = requests.get(f"{PODS_API}/{pod_id}", headers=HEADERS)
-    pod_data = response.json()
-    ssh_ip = pod_data["publicIp"]
-    ssh_port = pod_data["portMappings"]["22"]
-
-    # Copy the repository to the pod using scp
-    repo_dir = os.path.abspath(os.getcwd())
-    repo_name = os.path.basename(repo_dir)
-
-    print(f"Copying repository from {repo_dir} to RunPod...")
-
-    tar_command = [
-        "tar", "-czf", "/tmp/repo.tar.gz", "-C",
-        os.path.dirname(repo_dir), repo_name
-    ]
-    subprocess.run(tar_command, check=True)
-
-    # Copy the tarball to the pod
-    scp_command = [
-        "scp", "-o", "StrictHostKeyChecking=no", "-o",
-        "UserKnownHostsFile=/dev/null", "-o", "ServerAliveInterval=60", "-o",
-        "ServerAliveCountMax=10", "-P",
-        str(ssh_port), "/tmp/repo.tar.gz", f"root@{ssh_ip}:/tmp/"
-    ]
-    subprocess.run(scp_command, check=True)
-
-    # For custom image, we can use the pre-configured environment
-    setup_steps = [
-        "tar -xzf /tmp/repo.tar.gz --no-same-owner -C /workspace/",
-        f"cd /workspace/{repo_name}",
-        "source $HOME/.local/bin/env && source /opt/venv/bin/activate",
-        args.test_command
-    ]
-    
-    remote_command = " && ".join(setup_steps)
-
-    ssh_command = [
-        "ssh", "-o", "StrictHostKeyChecking=no", "-o",
-        "UserKnownHostsFile=/dev/null", "-o", "ServerAliveInterval=60", "-o",
-        "ServerAliveCountMax=10", "-p",
-        str(ssh_port), f"root@{ssh_ip}", remote_command
-    ]
-
-    print(f"Connecting to {ssh_ip}:{ssh_port}...")
-
-    try:
-        process = subprocess.Popen(ssh_command,
-                                   stdout=subprocess.PIPE,
-                                   stderr=subprocess.STDOUT,
-                                   universal_newlines=True,
-                                   bufsize=0)
-
-        stdout_lines = []
-
-        print("Command output:")
-
-        for line in iter(process.stdout.readline, ''):
-            print(line.strip())
-            stdout_lines.append(line)
-
-        process.wait()
-
-        return_code = process.returncode
-        success = return_code == 0
-
-        stdout_str = "".join(stdout_lines)
-
-        if success:
-            print("Command executed successfully")
-        else:
-            print(f"Command failed with exit code {return_code}")
-
-        result = {
-            "success": success,
-            "return_code": return_code,
-            "stdout": stdout_str,
-            "stderr": ""
-        }
-        return result
-
-    except Exception as e:
-        print(f"Error executing SSH command: {str(e)}")
-        result = {"success": False, "error": str(e), "stdout": "", "stderr": ""}
-        return result
-
-
-def terminate_pod(pod_id):
-    """Terminate the pod"""
-    print("Terminating RunPod...")
-    requests.delete(f"{PODS_API}/{pod_id}", headers=HEADERS)
-    print(f"Terminated pod {pod_id}")
-
-
-def main():
-    pod_id = None
-    try:
-        pod_id = create_pod()
-        wait_for_pod(pod_id)
-        result = execute_command(pod_id)
-
-        if result.get("error") is not None:
-            print(f"Error executing command: {result['error']}")
-            sys.exit(1)
-
-        if not result.get("success", False):
-            print(
-                "Tests failed - check the output above for details on which tests failed"
-            )
-            sys.exit(1)
-
-    finally:
-        if pod_id:
-            terminate_pod(pod_id)
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/runpod_cleanup.py

@@ -1,90 +0,0 @@
-import json
-import os
-import sys
-import uuid
-
-import requests
-
-API_KEY = os.environ['RUNPOD_API_KEY']
-RUN_ID = os.environ.get('GITHUB_RUN_ID', str(uuid.uuid4()))
-PODS_API = "https://rest.runpod.io/v1/pods"
-HEADERS = {
-    "Content-Type": "application/json",
-    "Authorization": f"Bearer {API_KEY}"
-}
-
-
-def get_job_ids():
-    """Parse job IDs from environment variable"""
-    job_ids_str = os.environ.get('JOB_IDS')
-    try:
-        job_ids = json.loads(job_ids_str)
-        if not isinstance(job_ids, list):
-            print("Error: JOB_IDS is not a list.")
-            sys.exit(1)
-        return job_ids
-    except json.JSONDecodeError as e:
-        print(f"Error parsing JOB_IDS: {e}")
-        sys.exit(1)
-
-
-def cleanup_pods():
-    """Find and terminate RunPod instances"""
-    print(f"Run ID: {RUN_ID}")
-
-    single_job_id = os.environ.get('JOB_ID')
-    
-    if single_job_id:
-        job_ids = [single_job_id]
-        print(f"Job ID: {single_job_id}")
-    else:
-        job_ids = get_job_ids()
-        print(f"Job IDs: {job_ids}")
-
-    # Get all pods associated with RunPod API_KEY
-    try:
-        response = requests.get(PODS_API, headers=HEADERS)
-        response.raise_for_status()
-        pods = response.json()
-    except requests.exceptions.RequestException as e:
-        print(f"Error getting pods: {e}")
-        sys.exit(1)
-
-    # Find and terminate pods created by this workflow run
-    terminated_pods = []
-    for pod in pods:
-        pod_name = pod.get("name", "")
-        pod_id = pod.get("id")
-
-        # Check if this pod was created by one of our jobs
-        if any(f"{job_id}-{RUN_ID}" in pod_name for job_id in job_ids):
-            print(f"Found pod: {pod_id} ({pod_name})")
-            try:
-                print(f"Terminating pod {pod_id}...")
-                term_response = requests.delete(f"{PODS_API}/{pod_id}",
-                                                headers=HEADERS)
-                term_response.raise_for_status()
-                terminated_pods.append(pod_id)
-                print(f"Successfully terminated pod {pod_id}")
-            except requests.exceptions.RequestException as e:
-                print(f"Error terminating pod {pod_id}: {e}")
-                sys.exit(1)
-    
-    if terminated_pods:
-        if single_job_id:
-            print(f"Terminated pod: {terminated_pods[0]}")
-        else:
-            print(f"Terminated {len(terminated_pods)} pods: {terminated_pods}")
-    else:
-        if single_job_id:
-            print(f"No pod found matching pattern: {single_job_id}-{RUN_ID}")
-        else:
-            print("No pods found to terminate.")
-
-
-def main():
-    cleanup_pods()
-
-
-if __name__ == "__main__":
-    main()

.github/workflows/ci-aggregate-status.yml

@@ -0,0 +1,80 @@
+name: Aggregate Test Status
+
+on:
+  status:
+
+permissions:
+  statuses: write
+
+jobs:
+  aggregate:
+    if: >-
+      github.event.context == 'direct-test-completed'
+      && github.event.state == 'success'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check and update aggregate status
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const sha = context.payload.sha;
+
+            const { data } = await github.rest.repos.getCombinedStatusForRef({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              ref: sha,
+              per_page: 100,
+            });
+
+            const bkStatuses = data.statuses.filter(
+              s => s.context.startsWith('buildkite/ci/')
+            );
+
+            const FASTCHECK_PREFIX = 'buildkite/ci/microscope-';
+            const FULL_SUITE_PREFIXES = [
+              'buildkite/ci/test-tube-',
+              'buildkite/ci/bar-chart-',
+            ];
+
+            const fastcheck = bkStatuses.filter(
+              s => s.context.startsWith(FASTCHECK_PREFIX)
+            );
+            const fullSuite = bkStatuses.filter(
+              s => FULL_SUITE_PREFIXES.some(p => s.context.startsWith(p))
+            );
+
+            if (
+              fastcheck.length > 0
+              && fastcheck.every(s => s.state === 'success')
+            ) {
+              core.info(
+                `All ${fastcheck.length} fastcheck tests passed — updating fastcheck-passed`
+              );
+              await github.rest.repos.createCommitStatus({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                sha,
+                state: 'success',
+                context: 'fastcheck-passed',
+                description:
+                  `All ${fastcheck.length} fastcheck tests passed`,
+              });
+            }
+
+            if (
+              fullSuite.length > 0
+              && fullSuite.every(s => s.state === 'success')
+            ) {
+              core.info(
+                `All ${fullSuite.length} full suite tests passed — updating full-suite-passed`
+              );
+              await github.rest.repos.createCommitStatus({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                sha,
+                state: 'success',
+                context: 'full-suite-passed',
+                description:
+                  `All ${fullSuite.length} full suite tests passed`,
+              });
+            }

.github/workflows/ci-precommit.yml

@@ -0,0 +1,32 @@
+name: pre-commit
+
+on:
+  pull_request:
+    branches: [main]
+  workflow_call:
+    inputs:
+      ref:
+        description: 'Git ref to checkout (defaults to github.ref)'
+        required: false
+        type: string
+
+permissions:
+  contents: read
+
+jobs:
+  pre-commit:
+    if: github.event_name == 'workflow_call' || github.event.pull_request.draft != true
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        ref: ${{ inputs.ref || '' }}
+    - uses: actions/setup-python@v5
+      with:
+        python-version: "3.12"
+    - run: echo "::add-matcher::.github/workflows/matchers/actionlint.json"
+    - run: echo "::add-matcher::.github/workflows/matchers/mypy.json"
+    - run: echo "::add-matcher::.github/workflows/matchers/ruff.json"
+    - uses: pre-commit/action@v3.0.1
+      with:
+        extra_args: --all-files --hook-stage manual

.github/workflows/ci-slash-commands.yml

@@ -0,0 +1,271 @@
+name: Slash Commands
+
+on:
+  issue_comment:
+    types: [created]
+
+permissions:
+  contents: read
+  pull-requests: write
+  statuses: write
+
+jobs:
+  handle-merge:
+    if: >-
+      github.event.issue.pull_request != null
+      && startsWith(github.event.comment.body, '/merge')
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check write permission
+        id: perm
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const { data: perm } = await github.rest.repos.getCollaboratorPermissionLevel({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              username: context.payload.comment.user.login,
+            });
+            const hasWrite = ['admin', 'write'].includes(perm.permission);
+            if (!hasWrite) {
+              core.setFailed(`User ${context.payload.comment.user.login} lacks write permission (has: ${perm.permission}).`);
+            }
+            core.setOutput('has_write', String(hasWrite));
+
+      - name: Add ready label and react
+        id: label
+        if: steps.perm.outputs.has_write == 'true'
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const owner = context.repo.owner;
+            const repo = context.repo.repo;
+            const prNumber = context.payload.issue.number;
+            try { await github.rest.issues.removeLabel({ owner, repo, issue_number: prNumber, name: 'ready' }); } catch {}
+            await github.rest.issues.addLabels({ owner, repo, issue_number: prNumber, labels: ['ready'] });
+            await github.rest.reactions.createForIssueComment({
+              owner, repo,
+              comment_id: context.payload.comment.id,
+              content: 'rocket',
+            });
+            const { data: pr } = await github.rest.pulls.get({ owner, repo, pull_number: prNumber });
+            core.setOutput('pr_sha', pr.head.sha);
+            core.setOutput('pr_branch', pr.head.ref);
+            core.setOutput('pr_number', String(prNumber));
+
+      - name: Trigger Full Suite
+        if: steps.perm.outputs.has_write == 'true'
+        env:
+          BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
+          PR_SHA: ${{ steps.label.outputs.pr_sha }}
+          PR_BRANCH: ${{ steps.label.outputs.pr_branch }}
+          PR_NUMBER: ${{ steps.label.outputs.pr_number }}
+          BK_ORG: ${{ vars.BUILDKITE_ORG_SLUG }}
+          BK_PIPELINE: ${{ vars.BUILDKITE_PIPELINE_SLUG }}
+        run: |
+          curl -sS --fail-with-body -X POST \
+            "https://api.buildkite.com/v2/organizations/${BK_ORG}/pipelines/${BK_PIPELINE}/builds" \
+            -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+            -H "Content-Type: application/json" \
+            --data-raw "$(jq -n \
+              --arg commit "$PR_SHA" \
+              --arg branch "$PR_BRANCH" \
+              --arg message "Full Suite for PR #${PR_NUMBER} (via /merge)" \
+              --argjson pr_id "$PR_NUMBER" \
+              '{
+                commit: $commit,
+                branch: $branch,
+                message: $message,
+                ignore_pipeline_branch_filters: true,
+                pull_request_id: $pr_id,
+                pull_request_base_branch: "main",
+                env: {
+                  TEST_SCOPE: "full",
+                  FULL_SUITE: "true",
+                  PR_NUMBER: ($pr_id | tostring)
+                }
+              }')"
+
+  parse-command:
+    if: >-
+      github.event.issue.pull_request != null
+      && startsWith(github.event.comment.body, '/test')
+    runs-on: ubuntu-latest
+    outputs:
+      test_type: ${{ steps.parse.outputs.test_type }}
+      test_scope: ${{ steps.parse.outputs.test_scope }}
+      full_suite: ${{ steps.parse.outputs.full_suite }}
+      pr_sha: ${{ steps.pr.outputs.sha }}
+      pr_branch: ${{ steps.pr.outputs.branch }}
+      has_write: ${{ steps.perm.outputs.has_write }}
+    steps:
+      - name: Check write permission
+        id: perm
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const { data: perm } = await github.rest.repos.getCollaboratorPermissionLevel({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              username: context.payload.comment.user.login,
+            });
+            const hasWrite = ['admin', 'write'].includes(perm.permission);
+            core.setOutput('has_write', String(hasWrite));
+            if (!hasWrite) {
+              core.info(`User ${context.payload.comment.user.login} lacks write permission — ignoring.`);
+            }
+
+      - name: Parse /test command
+        id: parse
+        if: steps.perm.outputs.has_write == 'true'
+        shell: bash
+        env:
+          COMMENT: ${{ github.event.comment.body }}
+        run: |
+          set -euo pipefail
+          TEST_NAME=$(echo "$COMMENT" | grep -oP '(?<=/test\s)\S+' | head -1 || true)
+
+          VALID="encoder vae transformer kernel unit ssim training lora-inference lora-training distillation self-forcing vsa vmoba performance api full fastcheck pre-commit"
+          if [ -z "$TEST_NAME" ] || ! echo "$VALID" | grep -qw "$TEST_NAME"; then
+            echo "Unknown test: '$TEST_NAME'. Valid: $VALID"
+            exit 1
+          fi
+
+          declare -A MAP=(
+            [encoder]=encoder [vae]=vae [transformer]=transformer
+            [kernel]=kernel_tests [unit]=unit_test
+            [ssim]=ssim [training]=training
+            [lora-inference]=inference_lora [lora-training]=training_lora
+            [distillation]=distillation_dmd [self-forcing]=self_forcing
+            [vsa]=training_vsa [vmoba]=inference_vmoba
+            [performance]=performance [api]=api_server
+          )
+
+          if [ "$TEST_NAME" = "full" ]; then
+            {
+              echo "test_type=all"
+              echo "test_scope=full"
+              echo "full_suite=true"
+            } >> "$GITHUB_OUTPUT"
+          elif [ "$TEST_NAME" = "fastcheck" ]; then
+            {
+              echo "test_type=fastcheck"
+              echo "test_scope=fastcheck"
+              echo "full_suite=false"
+            } >> "$GITHUB_OUTPUT"
+          elif [ "$TEST_NAME" = "pre-commit" ]; then
+            {
+              echo "test_type="
+              echo "test_scope=precommit"
+              echo "full_suite=false"
+            } >> "$GITHUB_OUTPUT"
+          else
+            {
+              echo "test_type=${MAP[$TEST_NAME]}"
+              echo "test_scope=direct"
+              echo "full_suite=false"
+            } >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Get PR details
+        id: pr
+        if: steps.perm.outputs.has_write == 'true'
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const { data: pr } = await github.rest.pulls.get({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: context.payload.issue.number,
+            });
+            core.setOutput('sha', pr.head.sha);
+            core.setOutput('branch', pr.head.ref);
+
+      - name: React to comment
+        if: steps.perm.outputs.has_write == 'true'
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            await github.rest.reactions.createForIssueComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              comment_id: context.payload.comment.id,
+              content: 'rocket',
+            });
+
+  pre-commit:
+    needs: parse-command
+    if: >-
+      needs.parse-command.outputs.has_write == 'true'
+      && needs.parse-command.outputs.test_scope == 'precommit'
+    uses: ./.github/workflows/ci-precommit.yml
+    with:
+      ref: refs/pull/${{ github.event.issue.number }}/merge
+
+  post-precommit-status:
+    needs: [parse-command, pre-commit]
+    if: always() && needs.parse-command.outputs.test_scope == 'precommit'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        env:
+          PR_SHA: ${{ needs.parse-command.outputs.pr_sha }}
+          RESULT: ${{ needs.pre-commit.result }}
+        with:
+          script: |
+            const state = process.env.RESULT === 'success' ? 'success' : 'failure';
+            await github.rest.repos.createCommitStatus({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              sha: process.env.PR_SHA,
+              state,
+              context: 'pre-commit',
+              description: `Triggered via /test pre-commit (${state})`,
+            });
+
+  trigger-buildkite:
+    needs: parse-command
+    if: >-
+      needs.parse-command.outputs.has_write == 'true'
+      && needs.parse-command.outputs.test_type != ''
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger Buildkite
+        env:
+          BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
+          PR_SHA: ${{ needs.parse-command.outputs.pr_sha }}
+          PR_BRANCH: ${{ needs.parse-command.outputs.pr_branch }}
+          PR_NUMBER: ${{ github.event.issue.number }}
+          TEST_SCOPE: ${{ needs.parse-command.outputs.test_scope }}
+          FULL_SUITE: ${{ needs.parse-command.outputs.full_suite }}
+          TEST_TYPE: ${{ needs.parse-command.outputs.test_type }}
+          BK_ORG: ${{ vars.BUILDKITE_ORG_SLUG }}
+          BK_PIPELINE: ${{ vars.BUILDKITE_PIPELINE_SLUG }}
+        run: |
+          curl -sS --fail-with-body -X POST \
+            "https://api.buildkite.com/v2/organizations/${BK_ORG}/pipelines/${BK_PIPELINE}/builds" \
+            -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+            -H "Content-Type: application/json" \
+            --data-raw "$(jq -n \
+              --arg commit "$PR_SHA" \
+              --arg branch "$PR_BRANCH" \
+              --arg message "/test ${TEST_TYPE} on PR #${PR_NUMBER}" \
+              --argjson pr_id "$PR_NUMBER" \
+              --arg test_scope "$TEST_SCOPE" \
+              --arg full_suite "$FULL_SUITE" \
+              --arg test_type "$TEST_TYPE" \
+              --arg pr_number "$PR_NUMBER" \
+              '{
+                commit: $commit,
+                branch: $branch,
+                message: $message,
+                ignore_pipeline_branch_filters: true,
+                pull_request_id: $pr_id,
+                pull_request_base_branch: "main",
+                env: {
+                  TEST_SCOPE: $test_scope,
+                  FULL_SUITE: $full_suite,
+                  TEST_TYPE: $test_type,
+                  PR_NUMBER: $pr_number
+                }
+              }')"

.github/workflows/ci-trigger-full-suite.yml

@@ -0,0 +1,83 @@
+name: Trigger Full Suite
+
+on:
+  pull_request_target:
+    types: [labeled, synchronize]
+
+permissions:
+  contents: read
+  pull-requests: read
+
+concurrency:
+  group: full-suite-${{ github.event.pull_request.number }}
+  cancel-in-progress: false
+
+jobs:
+  trigger:
+    if: >-
+      (github.event.action == 'labeled' && github.event.label.name == 'ready')
+      || github.event.action == 'synchronize'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check ready label
+        id: check
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const { data: pr } = await github.rest.pulls.get({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: context.payload.pull_request.number,
+            });
+            const hasReady = pr.labels.some(l => l.name === 'ready');
+            core.setOutput('has_ready', String(hasReady));
+            if (!hasReady) core.info('No ready label — skipping Full Suite trigger.');
+
+      - name: Cancel previous Buildkite builds
+        if: steps.check.outputs.has_ready == 'true'
+        env:
+          BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+        run: |
+          # Find running builds for this branch with TEST_SCOPE=full and cancel them
+          builds=$(curl -sS -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+            "https://api.buildkite.com/v2/organizations/${{ vars.BUILDKITE_ORG_SLUG }}/pipelines/${{ vars.BUILDKITE_PIPELINE_SLUG }}/builds?branch=${PR_BRANCH}&state=running,scheduled" \
+            | jq -r '.[] | select(try (.env.TEST_SCOPE == "full") catch false) | .number')
+          for build_num in $builds; do
+            echo "Cancelling Buildkite build #$build_num"
+            curl -sS -X PUT -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+              "https://api.buildkite.com/v2/organizations/${{ vars.BUILDKITE_ORG_SLUG }}/pipelines/${{ vars.BUILDKITE_PIPELINE_SLUG }}/builds/${build_num}/cancel"
+          done
+
+      - name: Trigger Buildkite Full Suite
+        if: steps.check.outputs.has_ready == 'true'
+        env:
+          BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
+          PR_SHA: ${{ github.event.pull_request.head.sha }}
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          BK_ORG: ${{ vars.BUILDKITE_ORG_SLUG }}
+          BK_PIPELINE: ${{ vars.BUILDKITE_PIPELINE_SLUG }}
+        run: |
+          curl -sS --fail-with-body -X POST \
+            "https://api.buildkite.com/v2/organizations/${BK_ORG}/pipelines/${BK_PIPELINE}/builds" \
+            -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
+            -H "Content-Type: application/json" \
+            --data-raw "$(jq -n \
+              --arg commit "$PR_SHA" \
+              --arg branch "$PR_BRANCH" \
+              --arg message "Full Suite for PR #${PR_NUMBER}" \
+              --argjson pr_id "$PR_NUMBER" \
+              '{
+                commit: $commit,
+                branch: $branch,
+                message: $message,
+                ignore_pipeline_branch_filters: true,
+                pull_request_id: $pr_id,
+                pull_request_base_branch: "main",
+                env: {
+                  TEST_SCOPE: "full",
+                  FULL_SUITE: "true",
+                  PR_NUMBER: ($pr_id | tostring)
+                }
+              }')"

.github/workflows/community-issue-labeler.yml

@@ -0,0 +1,65 @@
+name: Auto-Label Issues
+
+on:
+  issues:
+    types: [opened, edited]
+
+permissions:
+  issues: write
+
+jobs:
+  label-issues:
+    if: github.repository == 'hao-ai-lab/FastVideo'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Label by keywords
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const title = context.payload.issue.title.toLowerCase();
+            const body = (context.payload.issue.body || '').toLowerCase();
+            const text = title + ' ' + body;
+            const labels = [];
+
+            const rules = [
+              // scope labels (shared with PR labeling via Mergify)
+              // Mapping: label → repo directories
+              //   scope: training    → fastvideo/train/, fastvideo/training/, fastvideo/distillation/
+              //   scope: inference   → fastvideo/pipelines/, fastvideo/entrypoints/, fastvideo/worker/
+              //   scope: attention   → fastvideo/attention/
+              //   scope: kernel      → fastvideo-kernel/, csrc/
+              //   scope: model       → fastvideo/models/, fastvideo/layers/, fastvideo/configs/models/
+              //   scope: data        → fastvideo/dataset/, fastvideo/pipelines/preprocess/
+              //   scope: distributed → fastvideo/distributed/
+              //   scope: docs        → docs/
+              { keywords: ['training', 'finetune', 'fine-tune', 'lora', 'fsdp', 'distill'], label: 'scope: training' },
+              { keywords: ['inference', 'generate', 'pipeline', 'slow', 'latency'], label: 'scope: inference' },
+              { keywords: ['attention', 'vsa', 'flash', 'sta', 'vmoba', 'sparse attn'], label: 'scope: attention' },
+              { keywords: ['kernel', 'csrc', 'cuda kernel', 'thunderkittens'], label: 'scope: kernel' },
+              { keywords: ['wan', 'hunyuan', 'mochi', 'ltx', 'cogvideo', 'flux', 'sd3', 'cosmos'], label: 'scope: model' },
+              { keywords: ['dataset', 'dataloader', 'preprocessing', 'preprocess'], label: 'scope: data' },
+              { keywords: ['distributed', 'sequence parallel', 'fsdp', 'tensor parallel', 'multi-node', 'multi-gpu'], label: 'scope: distributed' },
+              { keywords: ['docs', 'documentation', 'tutorial', 'example'], label: 'scope: docs' },
+              // issue-only labels (cross-module, no single repo directory)
+              { keywords: ['install', 'setup', 'pip', 'cuda', 'uv ', 'import error', 'modulenotfound'], label: 'installation' },
+              { keywords: ['memory', 'oom', 'out of memory', 'gpu memory', 'vram'], label: 'performance' },
+              { keywords: ['windows', 'macos', 'mac os', 'apple', 'mps', 'rocm', 'amd', 'npu'], label: 'platform' },
+            ];
+
+            for (const rule of rules) {
+              if (rule.keywords.some(kw => text.includes(kw))) {
+                labels.push(rule.label);
+              }
+            }
+
+            if (labels.length > 0) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.payload.issue.number,
+                labels: labels,
+              });
+              console.log(`Added labels: ${labels.join(', ')}`);
+            } else {
+              console.log('No keyword matches found');
+            }

.github/workflows/community-stale.yml

@@ -0,0 +1,51 @@
+name: Close Stale Issues and PRs
+
+on:
+  schedule:
+    # Daily at 1:30 AM UTC
+    - cron: '30 1 * * *'
+
+jobs:
+  stale:
+    if: github.repository == 'hao-ai-lab/FastVideo'
+    permissions:
+      issues: write
+      pull-requests: write
+      actions: write
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # v10.1.1
+        with:
+          operations-per-run: 500
+
+          exempt-draft-pr: true
+          exempt-issue-labels: 'keep-open,pinned,security,Bug,RFC'
+          exempt-pr-labels: 'keep-open,pinned'
+
+          labels-to-add-when-unstale: 'unstale'
+          labels-to-remove-when-stale: 'unstale'
+
+          days-before-issue-stale: 90
+          days-before-issue-close: 30
+          stale-issue-label: 'stale'
+          stale-issue-message: >
+            This issue has been automatically marked as stale because it has not
+            had any activity within 90 days. It will be automatically closed if
+            no further activity occurs within 30 days. Leave a comment if you
+            feel this issue should remain open. Thank you!
+          close-issue-message: >
+            This issue has been automatically closed due to inactivity. Please
+            feel free to reopen if you feel it is still relevant. Thank you!
+
+          days-before-pr-stale: 60
+          days-before-pr-close: 14
+          stale-pr-label: 'stale'
+          stale-pr-message: >
+            This pull request has been automatically marked as stale because it
+            has not had any activity within 60 days. It will be automatically
+            closed if no further activity occurs within 14 days. Leave a comment
+            if you feel this pull request should remain open. Thank you!
+          close-pr-message: >
+            This pull request has been automatically closed due to inactivity.
+            Please feel free to reopen if you intend to continue working on it.
+            Thank you!

.github/workflows/community-welcome.yml

@@ -0,0 +1,56 @@
+name: Welcome First-Time Contributors
+
+on:
+  issues:
+    types: [opened]
+  pull_request_target:
+    types: [opened]
+
+permissions:
+  issues: write
+  pull-requests: write
+
+jobs:
+  welcome:
+    if: github.repository == 'hao-ai-lab/FastVideo'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/first-interaction@34f15e814fe48ac9312ccf29db4e74fa767cbab7 # v1.3.0
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          issue-message: |
+            Welcome to FastVideo! Thanks for opening your first issue.
+
+            To help us investigate, please include:
+            - **FastVideo version**: `pip show fastvideo`
+            - **GPU**: `nvidia-smi` output (GPU model, driver, CUDA version)
+            - **Python version**: `python --version`
+            - **OS**: e.g., Ubuntu 22.04
+
+            If this is a bug, a minimal reproduction script helps us fix it faster.
+
+            Useful links:
+            - [Documentation](https://hao-ai-lab.github.io/FastVideo)
+            - [Contributing Guide](https://hao-ai-lab.github.io/FastVideo/contributing/overview/)
+            - [Slack](https://join.slack.com/t/fastvideo/shared_invite/zt-3f4lao1uq-u~Ipx6Lt4J27AlD2y~IdLQ)
+          pr-message: |
+            Welcome to FastVideo! Thanks for your first pull request.
+
+            **How our CI works:**
+
+            PRs run a two-tier CI system:
+            1. **Pre-commit** — formatting (yapf), linting (ruff), type checking (mypy). Runs immediately on every PR.
+            2. **Fastcheck** — core GPU tests (encoders, VAEs, transformers, kernels, unit tests). Runs automatically via Buildkite on relevant file changes (~10-15 min).
+            3. **Full Suite** — integration tests, training pipelines, SSIM regression. Runs only when a reviewer adds the `ready` label.
+
+            **Before your PR is reviewed:**
+            - [ ] `pre-commit run --all-files` passes locally
+            - [ ] You've added or updated tests for your changes
+            - [ ] The PR description explains what and why
+
+            If pre-commit fails, a bot comment will explain how to fix it. Fastcheck and Full Suite results appear in the Checks section below.
+
+            **Useful links:**
+            - [Contributing Guide](https://hao-ai-lab.github.io/FastVideo/contributing/overview/)
+            - [Development Roadmap](https://github.com/hao-ai-lab/FastVideo/issues/899)
+            - [Slack](https://join.slack.com/t/fastvideo/shared_invite/zt-3f4lao1uq-u~Ipx6Lt4J27AlD2y~IdLQ)

.github/workflows/infra-build-image.yml

@@ -32,7 +32,7 @@ permissions:
 jobs:
   build-python-3-10:
     if: ${{ github.event.inputs.python_3_10 == 'true' }}
-    uses: ./.github/workflows/build-image-template.yml
+    uses: ./.github/workflows/_template-build-image.yml
     with:
       python_version: '3.10'
       dockerfile_path: docker/Dockerfile.python3.10
@@ -41,7 +41,7 @@ jobs:
 
   build-python-3-11:
     if: ${{ github.event.inputs.python_3_11 == 'true' }}
-    uses: ./.github/workflows/build-image-template.yml
+    uses: ./.github/workflows/_template-build-image.yml
     with:
       python_version: '3.11'
       dockerfile_path: docker/Dockerfile.python3.11
@@ -50,7 +50,7 @@ jobs:
 
   build-python-3-12:
     if: ${{ github.event.inputs.python_3_12 == 'true' }}
-    uses: ./.github/workflows/build-image-template.yml
+    uses: ./.github/workflows/_template-build-image.yml
     with:
       python_version: '3.12'
       dockerfile_path: docker/Dockerfile.python3.12
@@ -59,9 +59,9 @@ jobs:
 
   build-python-3-12-cuda-12-9:
     if: ${{ github.event.inputs.python_3_12_cuda_12_9 == 'true' }}
-    uses: ./.github/workflows/build-image-template.yml
+    uses: ./.github/workflows/_template-build-image.yml
     with:
       python_version: '3.12'
       dockerfile_path: docker/Dockerfile.python3.12.cuda12.9.1
       tag_suffix: py3.12-cuda12.9.1
-    secrets: inherit
+    secrets: inherit

.github/workflows/infra-docs.yml

@@ -7,14 +7,14 @@ on:
       - 'docs/**'
       - 'mkdocs.yml'
       - 'requirements-mkdocs.txt'
-      - '.github/workflows/docs.yml'
+      - '.github/workflows/infra-docs.yml'
   pull_request:
     branches: [ main ]
     paths:
       - 'docs/**'
       - 'mkdocs.yml'
       - 'requirements-mkdocs.txt'
-      - '.github/workflows/docs.yml'
+      - '.github/workflows/infra-docs.yml'
 
 permissions:
   contents: read
@@ -37,10 +37,11 @@ jobs:
         with:
           python-version: '3.12'
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
       - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements-mkdocs.txt
+        run: uv pip install --system -r requirements-mkdocs.txt
 
       - name: Setup Pages
         uses: actions/configure-pages@v4

.github/workflows/matchers/ruff.json

@@ -0,0 +1,17 @@
+{
+  "problemMatcher": [
+    {
+      "owner": "ruff",
+      "pattern": [
+        {
+          "regexp": "^(.+):(\\d+):(\\d+): (\\w+) (.+)$",
+          "file": 1,
+          "line": 2,
+          "column": 3,
+          "code": 4,
+          "message": 5
+        }
+      ]
+    }
+  ]
+}

.github/workflows/pr-test.yml

@@ -1,338 +0,0 @@
-name: PR Test
-
-on:
-  push:
-    branches: [main]
-    paths:
-      - "fastvideo/**/*.py"
-      - ".github/workflows/pr-test.yml"
-  pull_request:
-    branches: [main]
-    types: [opened, ready_for_review, synchronize, reopened]
-    paths:
-      - "fastvideo/**/*.py"
-      - ".github/workflows/pr-test.yml"
-      - "pyproject.toml"
-      - "docker/Dockerfile.python3.12"
-      - "csrc/**"
-  workflow_dispatch:
-    inputs:
-      run_encoder_test:
-        description: "Run encoder-test"
-        required: false
-        default: false
-        type: boolean
-      run_vae_test:
-        description: "Run vae-test"
-        required: false
-        default: false
-        type: boolean
-      run_transformer_test:
-        description: "Run transformer-test"
-        required: false
-        default: false
-        type: boolean
-      run_ssim_test:
-        description: "Run ssim-test"
-        required: false
-        default: false
-        type: boolean
-      run_training_test:
-        description: "Run training-test"
-        required: false
-        default: false
-        type: boolean
-      run_training_test_VSA:
-        description: "Run training-test-VSA"
-        required: false
-        default: false
-        type: boolean
-      run_precision_test_VSA:
-        description: "Run precision-test-VSA"
-        required: false
-        default: false
-        type: boolean
-      run_unit_test:
-        description: "Run unit-test"
-        required: false
-        default: false
-        type: boolean
-
-env:
-  PYTHONUNBUFFERED: "1"
-
-
-concurrency:
-  group: pr-test-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  pre-commit:
-    uses: ./.github/workflows/pre-commit.yml
-
-  change-filter:
-    runs-on: ubuntu-latest
-    needs: pre-commit
-    if: ${{ github.event.pull_request.draft == false || github.event_name == 'workflow_dispatch' }}
-    outputs:
-      encoder-test: ${{ steps.filter.outputs.encoder-test }}
-      vae-test: ${{ steps.filter.outputs.vae-test }}
-      transformer-test: ${{ steps.filter.outputs.transformer-test }}
-      training-test: ${{ steps.filter.outputs.training-test }}
-      training-test-VSA: ${{ steps.filter.outputs.training-test-VSA }}
-      precision-test-VSA: ${{ steps.filter.outputs.precision-test-VSA }}
-      unit-test: ${{ steps.filter.outputs.unit-test }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: dorny/paths-filter@v3
-        id: filter
-        with:
-          filters: |
-            # Define reusable path patterns
-            common-paths: &common-paths
-              - 'pyproject.toml'
-              - 'docker/Dockerfile.python3.10'
-              - 'docker/Dockerfile.python3.11'
-              - 'docker/Dockerfile.python3.12'
-            vsa-kernel-paths: &vsa-kernel-paths
-              - 'csrc/attn/video_sparse_attn/**'
-              - 'csrc/attn/video_sparse_attn/tk/**'
-              - 'csrc/attn/video_sparse_attn/setup.py'
-              - 'csrc/attn/video_sparse_attn/config_vsa.py'
-              - 'csrc/attn/video_sparse_attn/vsa.cpp'
-            vsa-paths: &vsa-paths
-              - 'fastvideo/**'
-              - *common-paths
-              - *vsa-kernel-paths
-            
-            # Actual tests
-            encoder-test:
-              - 'fastvideo/models/encoders/**'
-              - 'fastvideo/models/loader/**'
-              - 'fastvideo/tests/encoders/**'
-              - *common-paths
-            vae-test:
-              - 'fastvideo/models/vaes/**'
-              - 'fastvideo/models/loader/**'
-              - 'fastvideo/tests/vaes/**'
-              - *common-paths
-            transformer-test:
-              - 'fastvideo/models/dits/**'
-              - 'fastvideo/models/loader/**'
-              - 'fastvideo/tests/transformers/**'
-              - 'fastvideo/layers/**'
-              - 'fastvideo/attention/**'
-              - *common-paths
-            training-test:
-              - 'fastvideo/**'
-              - *common-paths
-            training-test-VSA:
-              - 'fastvideo/**'
-              - *common-paths
-              - *vsa-kernel-paths
-            precision-test-VSA:
-              - *common-paths
-              - *vsa-kernel-paths
-            unit-test:
-              - 'fastvideo/**'
-              - *common-paths
-
-  encoder-test:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.encoder-test == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_encoder_test == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "encoder-test"
-      gpu_type: "NVIDIA A40"
-      gpu_count: 1
-      volume_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "uv pip install -e .[test] && pytest ./fastvideo/tests/encoders -s"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-
-  vae-test:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.vae-test == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_vae_test == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "vae-test"
-      gpu_type: "NVIDIA A40"
-      gpu_count: 1
-      volume_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "uv pip install -e .[test] && pytest ./fastvideo/tests/vaes -s"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-
-  transformer-test:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.transformer-test == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_transformer_test == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "transformer-test"
-      gpu_type: "NVIDIA L40S"
-      gpu_count: 1
-      volume_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "uv pip install -e .[test] && pytest ./fastvideo/tests/transformers -s"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-      
-  ssim-test:
-    needs: change-filter
-    if: >-
-      github.event_name != 'workflow_dispatch' || (github.event_name == 'workflow_dispatch' && github.event.inputs.run_ssim_test == 'true')
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: [
-          # {version: "3.10", tag: "latest"},
-          # {version: "3.11", tag: "py3.11-latest"},
-          {version: "3.12", tag: "py3.12-latest"}
-        ]
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "ssim-test-py${{ matrix.python-version.version }}"
-      gpu_type: "NVIDIA A40"
-      gpu_count: 2
-      volume_size: 200
-      disk_size: 200
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:${{ matrix.python-version.tag }}"
-      test_command: "uv pip install -e .[test] && pytest ./fastvideo/tests/ssim -vs"
-      timeout_minutes: 60
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-
-  training-test:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.training-test == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_training_test == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "training-test"
-      gpu_type: "NVIDIA A40"
-      gpu_count: 4
-      volume_size: 100
-      disk_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "wandb login $WANDB_API_KEY && uv pip install -e .[test] && pytest ./fastvideo/tests/training/Vanilla -srP"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-      WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
-
-  training-test-VSA:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.training-test-VSA == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_training_test_VSA == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "training-test-VSA"
-      gpu_type: "NVIDIA H100 NVL"
-      gpu_count: 2
-      volume_size: 100
-      disk_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "wandb login $WANDB_API_KEY && uv pip install -e .[test] && pytest ./fastvideo/tests/training/VSA -srP"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-      WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
-
-  precision-test-VSA:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.precision-test-VSA == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_precision_test_VSA == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "precision-test-VSA"
-      gpu_type: "NVIDIA H100 NVL"
-      gpu_count: 1
-      volume_size: 100
-      disk_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "uv pip install -e .[test] && python csrc/attn/tests/test_vsa.py"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-
-  unit-test:
-    needs: change-filter
-    if: >-
-      (github.event_name != 'workflow_dispatch' && needs.change-filter.outputs.unit-test == 'true') || 
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_unit_test == 'true')
-    uses: ./.github/workflows/runpod-test.yml
-    with:
-      job_id: "unit-test"
-      gpu_type: "NVIDIA L40S"
-      gpu_count: 1
-      volume_size: 100
-      disk_size: 100
-      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "uv pip install -e .[test] && pytest ./fastvideo/dataset/ -vs && pytest ./fastvideo/workflow/ -vs && pytest ./fastvideo/entrypoints/ -vs"
-      timeout_minutes: 30
-    secrets:
-      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-      RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-
-  # nightly-test:
-  #   if: >-
-  #     (github.event_name == 'workflow_dispatch' && github.event.inputs.run_nightly_test == 'true')
-  #   uses: ./.github/workflows/runpod-test.yml
-  #   with:
-  #     job_id: "nightly-test"
-  #     gpu_type: "NVIDIA A40"
-  #     gpu_count: 4
-  #     volume_size: 100
-  #     disk_size: 100
-  #     image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-  #     test_command: "wandb login $WANDB_API_KEY && uv pip install -e .[test] && pytest ./fastvideo/tests/nightly/test_e2e_overfit_single_sample.py -vs"
-  #     timeout_minutes: 30
-  #   secrets:
-  #     RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-  #     RUNPOD_PRIVATE_KEY: ${{ secrets.RUNPOD_PRIVATE_KEY }}
-  #     WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
-
-  runpod-cleanup:
-    # Add other jobs to this list as you create them
-    needs: [encoder-test, vae-test, transformer-test, ssim-test, training-test, training-test-VSA, precision-test-VSA] 
-    if: ${{ always() && ((github.event_name != 'workflow_dispatch' && github.event.pull_request.draft == false) || github.event_name == 'workflow_dispatch') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-
-      - name: Install dependencies
-        run: pip install requests
-
-      - name: Cleanup all RunPod instances
-        env:
-          JOB_IDS: '["encoder-test", "vae-test", "transformer-test", "ssim-test-py3.10", "ssim-test-py3.11", "ssim-test-py3.12", "training-test", "training-test-VSA", "precision-test-VSA"]'
-          RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-          GITHUB_RUN_ID: ${{ github.run_id }}
-        run: python .github/scripts/runpod_cleanup.py

.github/workflows/pre-commit.yml

@@ -1,18 +0,0 @@
-name: pre-commit
-
-on:
-    workflow_call:
-
-jobs:
-  pre-commit:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-    - uses: actions/setup-python@v5
-      with:
-        python-version: "3.12"
-    - run: echo "::add-matcher::.github/workflows/matchers/actionlint.json"
-    - run: echo "::add-matcher::.github/workflows/matchers/mypy.json"
-    - uses: pre-commit/action@v3.0.1
-      with:
-        extra_args: --all-files --hook-stage manual

.github/workflows/publish-fastvideo.yml

@@ -56,10 +56,11 @@ jobs:
         with:
           python-version: '3.10'
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
       - name: Install build dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install build twine wheel
+        run: uv pip install --system build twine wheel
 
       - name: Build package
         run: |

.github/workflows/publish-kernel.yml

@@ -36,11 +36,11 @@ jobs:
           
           if [ "$NEW_VERSION" != "$OLD_VERSION" ]; then
             echo "Version changed from $OLD_VERSION to $NEW_VERSION"
-            echo "changed=true" >> $GITHUB_OUTPUT
-            echo "new-version=$NEW_VERSION" >> $GITHUB_OUTPUT
+            echo "changed=true" >> "$GITHUB_OUTPUT"
+            echo "new-version=$NEW_VERSION" >> "$GITHUB_OUTPUT"
           else
             echo "Version did not change"
-            echo "changed=false" >> $GITHUB_OUTPUT
+            echo "changed=false" >> "$GITHUB_OUTPUT"
           fi
 
   build_wheels:
@@ -131,11 +131,13 @@ jobs:
           clang-11 --version
           nvcc --version
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
       - name: Install PyTorch ${{ matrix.torch-cuda.torch-version }}+cu${{ matrix.torch-cuda.cuda-version }}
         run: |
-          pip install --upgrade pip
-          pip install typing-extensions==4.12.2
-          pip install --no-cache-dir torch==${{ matrix.torch-cuda.torch-version }} --index-url https://download.pytorch.org/whl/${{matrix.torch-cuda.torch-cuda-short}}
+          uv pip install --system typing-extensions==4.12.2
+          uv pip install --system --no-cache-dir torch==${{ matrix.torch-cuda.torch-version }} --index-url https://download.pytorch.org/whl/${{matrix.torch-cuda.torch-cuda-short}}
           nvcc --version
           python --version
           python -c "import torch; print('PyTorch:', torch.__version__)"
@@ -145,20 +147,20 @@ jobs:
       - name: Build wheel
         run: |
           export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
-          
-          pip install setuptools ninja packaging wheel triton scikit-build-core cmake build
-          
+
+          uv pip install --system setuptools ninja packaging wheel triton scikit-build-core cmake build
+
           cd fastvideo-kernel
           git submodule update --init --recursive  # Ensure ThunderKittens submodule is initialized
           # Release builds are produced on GPU-less runners, so force-enable TK and target Hopper.
           export TORCH_CUDA_ARCH_LIST="9.0a"
           export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
-          
+
           # Build standard wheel (no local version suffix) for PyPI
           python -m build --wheel --outdir dist
-          
+
           # Fix the wheel to be manylinux compliant
-          pip install auditwheel
+          uv pip install --system auditwheel
           # Point auditwheel at torch libs, but do not vendor them into the wheel.
           TORCH_LIB_DIR=$(python - <<'PY'
           import os
@@ -211,10 +213,13 @@ jobs:
           pattern: 'fastvideo_kernel-py*'
           merge-multiple: true
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
       - name: Build source distribution
         run: |
-          pip install build scikit-build-core cmake ninja
-          
+          uv pip install --system build scikit-build-core cmake ninja
+
           cd fastvideo-kernel
           # We don't need full CUDA/Torch to just package the source (sdist)
           python -m build --sdist --outdir dist

.github/workflows/runpod-test.yml

@@ -1,94 +0,0 @@
-name: RunPod Test
-
-on:
-  workflow_call:
-    inputs:
-      job_id:
-        required: true
-        type: string
-        description: "Unique identifier for this test job"
-      gpu_type:
-        required: true
-        type: string
-        description: "GPU type to use (e.g. NVIDIA A40, NVIDIA L40S)"
-      gpu_count:
-        required: true
-        type: number
-        description: "Number of GPUs to use"
-      volume_size:
-        required: false
-        type: number
-        default: 20
-        description: "Volume size in GB"
-      disk_size:
-        required: false
-        type: number
-        default: 20
-        description: "Disk size in GB"
-      image:
-        required: true
-        type: string
-        description: "Docker image to use"
-      test_command:
-        required: true
-        type: string
-        description: "Command to run tests"
-      timeout_minutes:
-        required: false
-        type: number
-        default: 30
-        description: "Timeout in minutes"
-    secrets:
-      RUNPOD_API_KEY:
-        required: true
-      RUNPOD_PRIVATE_KEY:
-        required: true
-      WANDB_API_KEY:
-        required: false
-
-jobs:
-  run-test:
-    runs-on: ubuntu-latest
-    environment: runpod-runners
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Set up SSH key
-        run: |
-          mkdir -p ~/.ssh
-          echo "${{ secrets.RUNPOD_PRIVATE_KEY }}" > ~/.ssh/id_rsa
-          chmod 600 ~/.ssh/id_rsa
-          ssh-keygen -y -f ~/.ssh/id_rsa > ~/.ssh/id_rsa.pub
-
-      - name: Install dependencies
-        run: pip install requests
-
-      - name: Run tests on RunPod
-        env:
-          JOB_ID: ${{ inputs.job_id }}
-          RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-          GITHUB_RUN_ID: ${{ github.run_id }}
-          WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }}
-        timeout-minutes: ${{ inputs.timeout_minutes }}
-        run: >-
-          python .github/scripts/runpod_api.py 
-          --gpu-type "${{ inputs.gpu_type }}"
-          --gpu-count ${{ inputs.gpu_count }}
-          --volume-size ${{ inputs.volume_size }}
-          --disk-size ${{ inputs.disk_size }}
-          --image "${{ inputs.image }}"
-          --test-command "${{ inputs.test_command }}"
-
-      - name: Terminate RunPod Instances
-        if: ${{ always() }}
-        env:
-          RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
-          GITHUB_RUN_ID: ${{ github.run_id }}
-          JOB_ID: ${{ inputs.job_id }}
-        run: python .github/scripts/runpod_cleanup.py 

.github/workflows/test.yml

@@ -1,31 +0,0 @@
-name: Run Tests
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'  # or any version you need
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip setuptools wheel
-          pip install torch
-          pip install packaging ninja
-          pip install -e .
-          pip install pytest
-
-      - name: Run Pytest
-        run: |
-          pytest --ignore csrc/attn/test

.github/workflows/vsa-publish.yml

@@ -1,257 +0,0 @@
-name: Publish Video Sparse Attention Kernel to PyPI on Version Change
-
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - "csrc/attn/video_sparse_attn/setup.py"
-  workflow_dispatch:
-
-jobs:
-  check-version-change:
-    runs-on: ubuntu-latest
-    outputs:
-      version-changed: ${{ steps.check-version.outputs.changed }}
-      new-version: ${{ steps.check-version.outputs.new-version }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
-
-      - name: Check if version changed
-        id: check-version
-        run: |
-          cd csrc/attn/video_sparse_attn
-          # Get current commit's version
-          NEW_VERSION=$(grep -oP 'VERSION\s*=\s*"\K[^"]+' setup.py)
-          echo "New version: $NEW_VERSION"
-          
-          # Get previous version from git history
-          OLD_VERSION=$(git show HEAD~1:./setup.py | grep -oP 'VERSION\s*=\s*"\K[^"]+' || echo "0.0.0")
-          echo "Old version: $OLD_VERSION"
-          
-          if [ "$NEW_VERSION" != "$OLD_VERSION" ]; then
-            echo "Version changed from $OLD_VERSION to $NEW_VERSION"
-            echo "changed=true" >> $GITHUB_OUTPUT
-            echo "new-version=$NEW_VERSION" >> $GITHUB_OUTPUT
-          else
-            echo "Version did not change"
-            echo "changed=false" >> $GITHUB_OUTPUT
-          fi
-
-  build_wheels:
-    name: Build Wheel
-    needs: check-version-change
-    if: ${{ needs.check-version-change.outputs.version-changed == 'true' || github.event_name == 'workflow_dispatch' }}
-    runs-on: ${{ matrix.os }}
-
-    strategy:
-      fail-fast: false
-      matrix:
-          # Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the
-          # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
-          os: [ubuntu-22.04]
-          python-version: ['3.10', '3.11', '3.12', '3.13']
-          # For version reference https://pytorch.org/get-started/previous-versions/
-          torch-cuda:
-            - torch-version: '2.5.1'
-              cuda-version: '12.4.1'
-              torch-cuda-short: 'cu124'
-            - torch-version: '2.6.0'
-              cuda-version: '12.6.3'
-              torch-cuda-short: 'cu126'
-            - torch-version: '2.7.1'
-              cuda-version: '12.8.0'
-              torch-cuda-short: 'cu128'
-
-    steps:
-      - name: Free up disk space
-        run: |
-          echo "Initial disk space:"
-          df -h
-          
-          # Remove large directories
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /usr/local/lib/android
-          sudo rm -rf /opt/ghc
-          sudo rm -rf /usr/local/share/boost
-          sudo rm -rf /usr/share/swift
-          sudo rm -rf /usr/local/lib/node_modules
-          sudo rm -rf /usr/local/share/powershell
-          sudo rm -rf /usr/share/rust
-          sudo rm -rf /usr/local/.ghcup
-          
-          # Remove cached files
-          sudo rm -rf /var/lib/apt/lists/*
-          sudo rm -rf /var/cache/apt/archives/*
-          
-          echo "Disk space after cleanup:"
-          df -h
-
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Install CUDA ${{ matrix.torch-cuda.cuda-version }}
-        uses: Jimver/cuda-toolkit@v0.2.21
-        id: cuda-toolkit
-        with:
-          cuda: ${{ matrix.torch-cuda.cuda-version }}
-          linux-local-args: '["--toolkit"]'
-          method: 'network'
-
-      - name: Install dependencies (GCC, Clang, CUDA Paths, Git)
-        run: |
-          sudo apt update
-          sudo apt install -y git patchelf gcc-11 g++-11 clang-11
-          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11
-
-          # Allow Git to Access Safe Directory
-          git config --global --add safe.directory /__w/FastVideo/FastVideo
-
-          # Set CUDA environment variables
-          export CUDA_HOME=/usr/local/cuda-${{ matrix.torch-cuda.cuda-version }}
-          export PATH=${CUDA_HOME}/bin:${PATH}
-          export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
-          
-          # Verify installation
-          gcc --version
-          g++ --version
-          clang-11 --version
-          nvcc --version
-
-      - name: Install PyTorch ${{ matrix.torch-cuda.torch-version }}+cu${{ matrix.torch-cuda.cuda-version }}
-        run: |
-          pip install --upgrade pip
-          # With python 3.13 and torch 2.5.1, unless we update typing-extensions, we get error
-          # AttributeError: attribute '__default__' of 'typing.ParamSpec' objects is not writable
-          pip install typing-extensions==4.12.2
-          # We want to figure out the CUDA version to download pytorch
-          # e.g. we can have system CUDA version being 11.7 but if torch==1.12 then we need to download the wheel from cu116
-          # see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
-          pip install --no-cache-dir torch==${{ matrix.torch-cuda.torch-version }} --index-url https://download.pytorch.org/whl/${{matrix.torch-cuda.torch-cuda-short}}
-          nvcc --version
-          python --version
-          python -c "import torch; print('PyTorch:', torch.__version__)"
-          python -c "import torch; print('CUDA:', torch.version.cuda)"
-          python -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"
-
-      - name: Build wheel
-        run: |
-          export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
-          
-          # We want setuptools >= 49.6.0 otherwise we can't compile the extension if system CUDA version is 11.7 and pytorch cuda version is 11.6
-          # https://github.com/pytorch/pytorch/blob/664058fa83f1d8eede5d66418abff6e20bd76ca8/torch/utils/cpp_extension.py#L810
-          # However this still fails so I'm using a newer version of setuptools
-          pip install setuptools
-          pip install ninja packaging wheel
-
-          cd csrc/attn/video_sparse_attn  # Move into the correct folder
-          git submodule update --init --recursive # Ensure ThunderKittens submodule is initialized
-          python setup.py bdist_wheel --dist-dir=dist
-
-      - name: Rename wheel file
-        run: |
-          cd csrc/attn/video_sparse_attn
-
-          CUDA_SHORT_VERSION=$(echo ${{ matrix.torch-cuda.cuda-version }} | cut -d. -f1,2 | sed 's/\.//g')
-          TORCH_SHORT_VERSION=$(echo ${{ matrix.torch-cuda.torch-version }} | cut -d. -f1,2)
-          # Get the correct version format
-          tmpname=cu${CUDA_SHORT_VERSION}torch${TORCH_SHORT_VERSION}
-          wheel_name=$(ls dist/*whl | xargs -n 1 basename | sed "s/-/+$tmpname-/2")
-          # Rename with version information
-          ls dist/*whl |xargs -I {} mv {} dist/${wheel_name}
-          echo "wheel_name=${wheel_name}" >> $GITHUB_ENV
-
-      - name: Upload wheel artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ env.wheel_name }}
-          path: csrc/attn/video_sparse_attn/dist/*.whl
-          retention-days: 90
-
-  publish_package:
-    name: Publish package
-    needs: [build_wheels, check-version-change]
-    if: ${{ needs.check-version-change.outputs.version-changed == 'true' || github.event_name == 'workflow_dispatch' }}
-    runs-on: ubuntu-22.04
-    permissions:
-      id-token: write  # Needed for OIDC Trusted Publishing
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-
-      - name: Install CUDA 12.4.1
-        uses: Jimver/cuda-toolkit@v0.2.21
-        id: cuda-toolkit
-        with:
-          cuda: 12.4.1
-          linux-local-args: '["--toolkit"]'
-          method: 'network'
-          sub-packages: '["nvcc"]'
-
-      - name: Install dependencies (GCC, Clang, CUDA Paths, Git)
-        run: |
-          sudo apt update
-          sudo apt install -y git patchelf gcc-11 g++-11 clang-11
-          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11
-
-          # Allow Git to Access Safe Directory
-          git config --global --add safe.directory /__w/FastVideo/FastVideo
-
-          # Set CUDA environment variables
-          export CUDA_HOME=/usr/local/cuda-12.4.1
-          export PATH=${CUDA_HOME}/bin:${PATH}
-          export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
-          
-          # Verify installation
-          gcc --version
-          g++ --version
-          clang-11 --version
-          nvcc --version
-
-      - name: Install PyTorch 2.5.1+cu12.4.1
-        run: |
-          pip install --upgrade pip
-          # With python 3.13 and torch 2.5.1, unless we update typing-extensions, we get error
-          # AttributeError: attribute '__default__' of 'typing.ParamSpec' objects is not writable
-          pip install typing-extensions==4.12.2
-          # We want to figure out the CUDA version to download pytorch
-          # e.g. we can have system CUDA version being 11.7 but if torch==1.12 then we need to download the wheel from cu116
-          # see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
-          export TORCH_CUDA_VERSION=124
-          pip install --no-cache-dir torch==2.5.1 --index-url https://download.pytorch.org/whl/cu${TORCH_CUDA_VERSION}
-          nvcc --version
-          python --version
-          python -c "import torch; print('PyTorch:', torch.__version__)"
-          python -c "import torch; print('CUDA:', torch.version.cuda)"
-          python -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"
-
-      - name: Build source distribution
-        run: |
-          export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
-          
-          # We want setuptools >= 49.6.0 otherwise we can't compile the extension if system CUDA version is 11.7 and pytorch cuda version is 11.6
-          # https://github.com/pytorch/pytorch/blob/664058fa83f1d8eede5d66418abff6e20bd76ca8/torch/utils/cpp_extension.py#L810
-          # However this still fails so I'm using a newer version of setuptools
-          pip install setuptools
-          pip install ninja packaging wheel
-
-          cd csrc/attn/video_sparse_attn  # Move into the correct folder
-          git submodule update --init --recursive # Ensure ThunderKittens submodule is initialized
-          python setup.py sdist --dist-dir=dist
-
-      - name: Publish release distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: csrc/attn/video_sparse_attn/dist/

.gitignore

@@ -33,6 +33,7 @@ env
 **.txt
 *.log
 weights/
+logs/
 
 # SSIM test outputs
 fastvideo/tests/ssim/generated_videos/
@@ -84,6 +85,18 @@ docs/distillation/examples/
 dmd_t2v_output/
 preprocess_output_text/
 
+# Next.js / Node artifacts under ui/: see ui/.gitignore
+
 .claude/
 .codex/
+.sisyphus/
 openspec/
+fastvideo/tests/ssim/reference_videos/**
+
+# Local clones of upstream repos used only for parity testing.
+/stable-audio-tools/
+/daVinci-MagiHuman/
+
+# Converted model weights (produced by scripts/checkpoint_conversion/*).
+# Tens of GB; should live on HF, not in git.
+/converted_weights/

.nvimlog

@@ -0,0 +1 @@
+WRN 2026-03-26T13:46:33.469 ?.19646    server_start:193: Failed to start server: operation not permitted: /var/folders/z_/h_6myyk14d1b7z87z3vy4mjh0000gn/T/nvim.dsynkd/iSe0el/nvim.19646.0

.pre-commit-config.yaml

@@ -7,22 +7,13 @@ exclude: |
     fastvideo-kernel/.*|
     assets/.*|
     tests/.*|
-    demo/.*|
-    predict\.py|
     scripts/.*|
-    assets/prompts/.*|
-    fastvideo/data_preprocess/.*|
     fastvideo/dataset/.*|
     fastvideo/models/.*|
-    fastvideo/sample/.*|
-    fastvideo/train\.py|
-    fastvideo/utils/.*|
     examples/.*|
-    .github/workflows/fastvideo-publish.yml|
-    .github/workflows/sta-publish.yml|
-    .github/workflows/vsa-publish.yml|
-    .github/workflows/build-image-template.yml|
-    docs/source/inference/support_matrix.md
+    \.agents/.*|
+    .github/workflows/publish-fastvideo.yml|
+    .github/workflows/_template-build-image.yml
   )
 repos:
 - repo: https://github.com/google/yapf

.python-version

@@ -0,0 +1 @@
+3.12

AGENTS.md

@@ -11,7 +11,7 @@
 - Static assets: `assets/` (including `assets/images/`, `assets/videos/`, and `assets/prompts/`) and `comfyui/assets/`.
 
 ## Build, Test, and Development Commands
-- `uv pip install -e .[dev]`: editable install with lint/test extras.
+- `uv pip install -e ".[dev]"`: editable install with lint/test extras.
 - `pre-commit install --hook-type pre-commit --hook-type commit-msg`: enable local hooks.
 - `pre-commit run --all-files`: run formatter/lint/type/spelling checks.
 - `pytest tests/`: run top-level test suite.
@@ -23,7 +23,8 @@
 - Python 3.10+; 4-space indentation; keep code and imports readable and explicit.
 - Style tools are configured in `pyproject.toml` and `.pre-commit-config.yaml`:
   - `yapf` (format), `ruff` (lint, auto-fix), `mypy` (typing), `codespell`.
-- Target line length is 80.
+- Lint via `pre-commit run --files <changed paths>` (or `pre-commit run --all-files` for a full sweep) before committing. Do not shell out to `yapf`/`ruff`/`codespell`/`mypy` directly — pre-commit chains them with the project's config and respects the `.pre-commit-config.yaml` excludes (e.g. `fastvideo/tests/` is intentionally skipped). If pre-commit reports `(no files to check)` for your paths, that exclude is deliberate — don't bypass it.
+- Target line length is 120 (configured in `pyproject.toml` for ruff, yapf, and isort).
 - Naming: `snake_case` for functions/files, `PascalCase` for classes, `UPPER_SNAKE_CASE` for constants.
 
 ## Testing Guidelines
@@ -54,3 +55,31 @@ This repository is agent-friendly. Before doing any work, read:
 If you are exploring a new procedure that has no existing SOP, document your
 progress in `.agents/exploration/` and flag it for review at the end of your
 session.
+
+## Per-Directory AGENTS.md
+
+Local guidance lives next to the code. Read the in-scope file before editing:
+
+| Directory | What it covers |
+|-----------|----------------|
+| `fastvideo/AGENTS.md` | Core package map, public API, registry-driven model dispatch |
+| `fastvideo/configs/AGENTS.md` | Arch + pipeline config dataclasses, `param_names_mapping` |
+| `fastvideo/models/AGENTS.md` | DiT / VAE / encoder / scheduler / loader layout (pre-commit excluded) |
+| `fastvideo/layers/AGENTS.md` | Tensor-parallel linear/attention layer rules for ports |
+| `fastvideo/attention/AGENTS.md` | Backend registry + env-var override |
+| `fastvideo/pipelines/AGENTS.md` | Stage ABC, `basic/<model>/`, `preprocess/`, presets |
+| `fastvideo/training/AGENTS.md` | Legacy monolithic pipelines (frozen for existing models) |
+| `fastvideo/train/AGENTS.md` | New modular trainer (methods × models × callbacks, YAML) |
+| `fastvideo/tests/AGENTS.md` | Test taxonomy, conftest, pre-commit-excluded path |
+| `fastvideo/tests/ssim/AGENTS.md` | GPU SSIM regression authoring + reference video sync |
+| `scripts/checkpoint_conversion/AGENTS.md` | Adding a converter for a new HF/official checkpoint |
+
+## Critical: Two Training Stacks Coexist
+
+- `fastvideo/training/` — legacy, monolithic per-model `*_training_pipeline.py` and
+  `*_distillation_pipeline.py`. Still authoritative for shipped models.
+- `fastvideo/train/` — new modular framework (composable methods × models × callbacks
+  driven by YAML). Preferred for new training work.
+
+Pick the matching stack before editing. Do not migrate a pipeline between them
+without an explicit ask — the conventions and config surfaces differ.

README.md

@@ -6,16 +6,17 @@
      | <a href="https://hao-ai-lab.github.io/FastVideo"><b>Documentation</b></a> | <a href="https://hao-ai-lab.github.io/FastVideo/inference/inference_quick_start/"><b> Quick Start</b></a> | <a href="https://github.com/hao-ai-lab/FastVideo/discussions/982"  target="_blank"><b>Weekly Dev Meeting</b></a>  | 🟣💬 <a href="https://join.slack.com/t/fastvideo/shared_invite/zt-3f4lao1uq-u~Ipx6Lt4J27AlD2y~IdLQ" target="_blank"> <b>Slack</b> </a> |  🟣💬 <a href="https://github.com/hao-ai-lab/FastVideo/discussions/1097" target="_blank"> <b> WeChat </b> </a> |
 </p>
 
-**FastVideo is a unified post-training and inference framework for accelerated video generation.**
+**FastVideo is a unified post-training and real-time inference framework for accelerated video generation.**
 
 ## NEWS
-
-- `2025/11/19`: Release [CausalWan2.2 I2V A14B Preview](https://huggingface.co/FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers) models, [Blog](https://hao-ai-lab.github.io/blogs/fastvideo_causalwan_preview/) and [Inference Code!](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py)
+- `2026/03/17`: Release Live demo: [Into the Dreamverse: Vibe Directing in FastVideo](https://dreamverse.fastvideo.org/), check out the [Blog](https://haoailab.com/blogs/dreamverse/).
+- `2026/03/13`: Release Live demo: [Create a 5s 1080p Video in 4.5s with FastVideo on a Single GPU](https://1080p.fastvideo.org/), check out the [Blog](https://haoailab.com/blogs/fastvideo_realtime_1080p/).
+- `2025/11/19`: Release [CausalWan2.2 I2V A14B Preview](https://huggingface.co/FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers) models, [Blog](https://hao-ai-lab.github.io/blogs/fastvideo_causalwan_preview/) and [Inference Code!](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py).
 - `2025/08/04`: Release [FastWan](https://hao-ai-lab.github.io/FastVideo/distillation/dmd) models and [Sparse-Distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/).
 
 ### More News
 
-- `2025/06/14`: Release finetuning and inference code for [VSA](https://arxiv.org/pdf/2505.13389)
+- `2025/06/14`: Release finetuning and inference code for [VSA](https://arxiv.org/pdf/2505.13389).
 - `2025/04/24`: [FastVideo V1](https://hao-ai-lab.github.io/blogs/fastvideo/) is released!
 - `2025/02/18`: Release the inference code for [Sliding Tile Attention](https://hao-ai-lab.github.io/blogs/sta/).
 

__init__.py

@@ -1,15 +1,10 @@
 try:
-    from .comfyui.video_generator.nodes import (NODE_CLASS_MAPPINGS,
-                                                NODE_DISPLAY_NAME_MAPPINGS)
+    from .comfyui.video_generator.nodes import (NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS)
     WEB_DIRECTORY = "./web"
-    __all__ = [
-        'NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS', 'WEB_DIRECTORY'
-    ]
+    __all__ = ['NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS', 'WEB_DIRECTORY']
 except ImportError:
     # ComfyUI environment not available, skip comfyui imports
     NODE_CLASS_MAPPINGS = {}
     NODE_DISPLAY_NAME_MAPPINGS = {}
     WEB_DIRECTORY = "./web"
-    __all__ = [
-        'NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS', 'WEB_DIRECTORY'
-    ]
+    __all__ = ['NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS', 'WEB_DIRECTORY']

benchmarks/fvd/__init__.py

@@ -13,8 +13,7 @@ from .fvd import (
     compute_statistics,
     FVDConfig,
 )
-from .feature_extractors import (BaseFeatureExtractor, I3DFeatureExtractor,
-                                 load_extractor)
+from .feature_extractors import (BaseFeatureExtractor, I3DFeatureExtractor, load_extractor)
 from .video_utils import (
     load_video_auto,
     sample_clips_from_video,

benchmarks/fvd/cli.py

@@ -5,18 +5,11 @@ from .fvd import compute_fvd_with_config, FVDConfig
 
 
 def main() -> int:
-    parser = argparse.ArgumentParser(
-        description='Compute Fréchet Video Distance (FVD)')
+    parser = argparse.ArgumentParser(description='Compute Fréchet Video Distance (FVD)')
 
     # Required arguments
-    parser.add_argument('--real-path',
-                        type=str,
-                        required=True,
-                        help='Path to real videos')
-    parser.add_argument('--gen-path',
-                        type=str,
-                        required=True,
-                        help='Path to generated videos')
+    parser.add_argument('--real-path', type=str, required=True, help='Path to real videos')
+    parser.add_argument('--gen-path', type=str, required=True, help='Path to generated videos')
 
     # Extractor selection
     parser.add_argument('--extractor',
@@ -26,42 +19,19 @@ def main() -> int:
                         help='Feature extractor model to use (default: i3d)')
 
     # Standard args
-    parser.add_argument('--seed',
-                        type=int,
-                        default=None,
-                        help='Random seed for reproducibility')
+    parser.add_argument('--seed', type=int, default=None, help='Random seed for reproducibility')
     parser.add_argument('--protocol',
                         type=str,
                         default=None,
                         choices=['fvd2048_16f', 'fvd2048_128f', 'quick_test'],
                         help='Use standard protocol (overrides other settings)')
-    parser.add_argument('--num-videos',
-                        type=int,
-                        default=2048,
-                        help='Number of videos to use')
-    parser.add_argument('--num-frames',
-                        type=int,
-                        default=16,
-                        help='Number of frames per clip')
-    parser.add_argument('--clip-strategy',
-                        type=str,
-                        default='beginning',
-                        help='Clip sampling strategy')
-    parser.add_argument('--batch-size',
-                        type=int,
-                        default=32,
-                        help='Batch size for feature extraction')
-    parser.add_argument('--device',
-                        type=str,
-                        default='cuda',
-                        help='Device to use (cuda or cpu)')
-    parser.add_argument('--cache-real-features',
-                        type=str,
-                        default=None,
-                        help='Path to cache real video features')
-    parser.add_argument('--quiet',
-                        action='store_true',
-                        help='Suppress progress output')
+    parser.add_argument('--num-videos', type=int, default=2048, help='Number of videos to use')
+    parser.add_argument('--num-frames', type=int, default=16, help='Number of frames per clip')
+    parser.add_argument('--clip-strategy', type=str, default='beginning', help='Clip sampling strategy')
+    parser.add_argument('--batch-size', type=int, default=32, help='Batch size for feature extraction')
+    parser.add_argument('--device', type=str, default='cuda', help='Device to use (cuda or cpu)')
+    parser.add_argument('--cache-real-features', type=str, default=None, help='Path to cache real video features')
+    parser.add_argument('--quiet', action='store_true', help='Suppress progress output')
 
     args = parser.parse_args()
 

benchmarks/fvd/feature_extractors.py

@@ -22,8 +22,7 @@ class BaseFeatureExtractor(ABC, nn.Module):
 
     def __init__(self, device: str = 'cuda'):
         super().__init__()
-        self.device = torch.device(
-            device if torch.cuda.is_available() else 'cpu')
+        self.device = torch.device(device if torch.cuda.is_available() else 'cpu')
 
     @property
     @abstractmethod
@@ -53,10 +52,7 @@ class BaseFeatureExtractor(ABC, nn.Module):
         pass
 
     @torch.no_grad()
-    def extract_features(self,
-                         videos: torch.Tensor,
-                         batch_size: int = 32,
-                         verbose: bool = True) -> torch.Tensor:
+    def extract_features(self, videos: torch.Tensor, batch_size: int = 32, verbose: bool = True) -> torch.Tensor:
         """
         Extract features for a large tensor of videos by batching.
         """
@@ -65,9 +61,7 @@ class BaseFeatureExtractor(ABC, nn.Module):
 
         iterator = range(0, N, batch_size)
         if verbose:
-            iterator = tqdm(
-                iterator,
-                desc=f"Extracting features ({self.__class__.__name__})")
+            iterator = tqdm(iterator, desc=f"Extracting features ({self.__class__.__name__})")
 
         for i in iterator:
             batch = videos[i:i + batch_size].to(self.device)
@@ -95,9 +89,7 @@ class I3DFeatureExtractor(BaseFeatureExtractor):
 
     def _load_model(self) -> torch.nn.Module:
         try:
-            model_path = hf_hub_download(repo_id=self.REPO_ID,
-                                         filename=self.MODEL_FILENAME,
-                                         cache_dir=self.cache_dir)
+            model_path = hf_hub_download(repo_id=self.REPO_ID, filename=self.MODEL_FILENAME, cache_dir=self.cache_dir)
             return torch.jit.load(model_path, map_location=self.device)
         except Exception as e:
             raise RuntimeError(f"Failed to load I3D model: {e}") from e
@@ -119,10 +111,7 @@ class I3DFeatureExtractor(BaseFeatureExtractor):
         # Resize to 224x224
         if H != 224 or W != 224:
             videos = videos.reshape(B * T, C, H, W)
-            videos = F.interpolate(videos,
-                                   size=(224, 224),
-                                   mode='bilinear',
-                                   align_corners=False)
+            videos = F.interpolate(videos, size=(224, 224), mode='bilinear', align_corners=False)
             videos = videos.reshape(B, T, C, 224, 224)
 
         # [B, T, C, H, W] -> [B, C, T, H, W]
@@ -131,21 +120,15 @@ class I3DFeatureExtractor(BaseFeatureExtractor):
     def extract_features_batch(self, videos: torch.Tensor) -> torch.Tensor:
         batch = self.preprocess(videos)
         # TorchScript I3D returns raw logits when return_features=True
-        return self.model(batch,
-                          rescale=False,
-                          resize=False,
-                          return_features=True)
+        return self.model(batch, rescale=False, resize=False, return_features=True)
 
 
 # 2. CLIP Extractor (Semantic/Content Quality)
 class CLIPFeatureExtractor(BaseFeatureExtractor):
 
-    def __init__(self,
-                 device: str = 'cuda',
-                 model_name: str = "openai/clip-vit-base-patch32"):
+    def __init__(self, device: str = 'cuda', model_name: str = "openai/clip-vit-base-patch32"):
         if not TRANSFORMERS_AVAILABLE:
-            raise ImportError(
-                "Please install transformers: pip install transformers")
+            raise ImportError("Please install transformers: uv pip install transformers")
         super().__init__(device)
         self.processor = CLIPProcessor.from_pretrained(model_name)
         self.model = CLIPModel.from_pretrained(model_name).to(self.device)
@@ -172,9 +155,7 @@ class CLIPFeatureExtractor(BaseFeatureExtractor):
         images = videos.view(B * T, C, H, W)
 
         # HF Processor
-        inputs = self.processor(images=images,
-                                return_tensors="pt",
-                                padding=True)
+        inputs = self.processor(images=images, return_tensors="pt", padding=True)
         inputs = {k: v.to(self.device) for k, v in inputs.items()}
 
         # Extract features [B*T, Dim]
@@ -188,24 +169,15 @@ class CLIPFeatureExtractor(BaseFeatureExtractor):
 # 3. VideoMAE Extractor (Structure/Motion Quality)
 class VideoMAEFeatureExtractor(BaseFeatureExtractor):
 
-    def __init__(self,
-                 device: str = 'cuda',
-                 model_name: str = "MCG-NJU/videomae-base"):
+    def __init__(self, device: str = 'cuda', model_name: str = "MCG-NJU/videomae-base"):
         if not TRANSFORMERS_AVAILABLE:
-            raise ImportError(
-                "Please install transformers: pip install transformers")
+            raise ImportError("Please install transformers: uv pip install transformers")
         super().__init__(device)
         self.model = VideoMAEModel.from_pretrained(model_name).to(self.device)
         self.model.eval()
 
-        self.register_buffer(
-            'mean',
-            torch.tensor([0.485, 0.456, 0.406],
-                         device=self.device).view(1, 1, 3, 1, 1))
-        self.register_buffer(
-            'std',
-            torch.tensor([0.229, 0.224, 0.225],
-                         device=self.device).view(1, 1, 3, 1, 1))
+        self.register_buffer('mean', torch.tensor([0.485, 0.456, 0.406], device=self.device).view(1, 1, 3, 1, 1))
+        self.register_buffer('std', torch.tensor([0.229, 0.224, 0.225], device=self.device).view(1, 1, 3, 1, 1))
 
     @property
     def feature_dim(self) -> int:
@@ -221,10 +193,7 @@ class VideoMAEFeatureExtractor(BaseFeatureExtractor):
         # 1. Resize to 224x224
         if H != 224 or W != 224:
             videos = videos.view(B * T, C, H, W)
-            videos = F.interpolate(videos,
-                                   size=(224, 224),
-                                   mode='bilinear',
-                                   align_corners=False)
+            videos = F.interpolate(videos, size=(224, 224), mode='bilinear', align_corners=False)
             videos = videos.view(B, T, C, 224, 224)
 
         # 2. Normalize to [0, 1]
@@ -260,5 +229,4 @@ def load_extractor(name: str, device: str = 'cuda') -> BaseFeatureExtractor:
     elif name == 'videomae':
         return VideoMAEFeatureExtractor(device)
     else:
-        raise ValueError(
-            f"Unknown extractor: {name}. Options: i3d, clip, videomae")
+        raise ValueError(f"Unknown extractor: {name}. Options: i3d, clip, videomae")

benchmarks/fvd/fvd.py

@@ -36,8 +36,7 @@ def compute_frechet_distance(mu1: np.ndarray,
 
     if np.iscomplexobj(covmean):
         if not np.allclose(np.diagonal(covmean).imag, 0, atol=1e-3):
-            print(
-                f"Warning: Imaginary component: {np.max(np.abs(covmean.imag))}")
+            print(f"Warning: Imaginary component: {np.max(np.abs(covmean.imag))}")
         covmean = covmean.real
 
     trace_product = np.trace(covmean)
@@ -67,8 +66,7 @@ class FVDConfig:
     temporal_stride: int = 1  # For sliding window clips
 
     # Data processing
-    video_extensions: list[str] = field(
-        default_factory=lambda: ['.mp4', '.avi', '.mov', '.mkv'])
+    video_extensions: list[str] = field(default_factory=lambda: ['.mp4', '.avi', '.mov', '.mkv'])
     support_frame_dirs: bool = True
 
     # Computation
@@ -88,25 +86,17 @@ class FVDConfig:
     @classmethod
     def fvd2048_16f(cls) -> 'FVDConfig':
         """Standard FVD protocol: 2048 videos, 16 frames, beginning clip."""
-        return cls(num_videos=2048,
-                   num_frames_per_clip=16,
-                   clip_strategy='beginning',
-                   use_streaming=True)
+        return cls(num_videos=2048, num_frames_per_clip=16, clip_strategy='beginning', use_streaming=True)
 
     @classmethod
     def fvd2048_128f(cls) -> 'FVDConfig':
         """Long video protocol: 2048 videos, 128 frames."""
-        return cls(num_videos=2048,
-                   num_frames_per_clip=128,
-                   clip_strategy='beginning',
-                   use_streaming=True)
+        return cls(num_videos=2048, num_frames_per_clip=128, clip_strategy='beginning', use_streaming=True)
 
     @classmethod
     def quick_test(cls) -> 'FVDConfig':
         """Quick test config: 100 videos, 16 frames."""
-        return cls(num_videos=100,
-                   num_frames_per_clip=16,
-                   clip_strategy='beginning')
+        return cls(num_videos=100, num_frames_per_clip=16, clip_strategy='beginning')
 
     def to_dict(self) -> dict:
         """Export config to dict for logging"""
@@ -196,14 +186,10 @@ def load_or_compute_features(videos: str | Path | torch.Tensor,
             max_features = config.num_videos * config.num_clips_per_video
 
             if len(features) < max_features:
-                print(
-                    f"WARNING: Cache has {len(features)} features but need {max_features}"
-                )
+                print(f"WARNING: Cache has {len(features)} features but need {max_features}")
                 print("Cached features insufficient - will recompute...")
             elif len(features) > max_features:
-                print(
-                    f"Using {max_features} features from cache (truncated from {len(features)})"
-                )
+                print(f"Using {max_features} features from cache (truncated from {len(features)})")
                 features = features[:max_features]
                 return features
             else:
@@ -215,17 +201,16 @@ def load_or_compute_features(videos: str | Path | torch.Tensor,
     if isinstance(videos, (str | Path)):
         target_size = (224, 224) if config.resize_before_extraction else None
 
-        video_generator = load_video_clips_streaming(
-            videos,
-            num_frames=config.num_frames_per_clip,
-            max_videos=config.num_videos,
-            clip_strategy=config.clip_strategy,
-            frame_stride=config.frame_stride,
-            num_clips_per_video=config.num_clips_per_video,
-            video_extensions=config.video_extensions,
-            support_frame_dirs=config.support_frame_dirs,
-            target_size=target_size,
-            verbose=True)
+        video_generator = load_video_clips_streaming(videos,
+                                                     num_frames=config.num_frames_per_clip,
+                                                     max_videos=config.num_videos,
+                                                     clip_strategy=config.clip_strategy,
+                                                     frame_stride=config.frame_stride,
+                                                     num_clips_per_video=config.num_clips_per_video,
+                                                     video_extensions=config.video_extensions,
+                                                     support_frame_dirs=config.support_frame_dirs,
+                                                     target_size=target_size,
+                                                     verbose=True)
 
         max_clips = config.num_videos * config.num_clips_per_video
         features = extract_features_streaming(video_generator,
@@ -235,17 +220,14 @@ def load_or_compute_features(videos: str | Path | torch.Tensor,
                                               verbose=True)
     else:
         print(f"Extracting features from {len(videos)} video tensors...")
-        features = extractor.extract_features(videos,
-                                              batch_size=config.batch_size,
-                                              verbose=True)
+        features = extractor.extract_features(videos, batch_size=config.batch_size, verbose=True)
         features = features.numpy()
 
     # Validate feature count
     expected_count = config.num_videos * config.num_clips_per_video
     if len(features) < expected_count:
-        raise ValueError(
-            f"ERROR: Only extracted {len(features)} features, but need {expected_count}!\n"
-            f"Found fewer videos than expected. Check your video directory.")
+        raise ValueError(f"ERROR: Only extracted {len(features)} features, but need {expected_count}!\n"
+                         f"Found fewer videos than expected. Check your video directory.")
     elif len(features) > expected_count:
         print(f"Truncating {len(features)} features to {expected_count}")
         features = features[:expected_count]
@@ -312,9 +294,7 @@ def compute_fvd_with_config(real_videos: str | Path | torch.Tensor,
 
     # Initialize Extractor using Factory
     if verbose:
-        print(
-            f"\nInitializing {config.extractor_model.upper()} model on {config.device}..."
-        )
+        print(f"\nInitializing {config.extractor_model.upper()} model on {config.device}...")
 
     extractor = load_extractor(config.extractor_model, device=config.device)
 
@@ -324,12 +304,11 @@ def compute_fvd_with_config(real_videos: str | Path | torch.Tensor,
         print("Extracting REAL video features...")
         print(f"{'='*70}")
 
-    real_features = load_or_compute_features(
-        videos=real_videos,
-        extractor=extractor,
-        config=config,
-        cache_path=config.cache_real_features,
-        cache_name="real_features")
+    real_features = load_or_compute_features(videos=real_videos,
+                                             extractor=extractor,
+                                             config=config,
+                                             cache_path=config.cache_real_features,
+                                             cache_name="real_features")
 
     if verbose:
         print(f"\n{'='*70}")

benchmarks/fvd/i3d_model.py

@@ -19,16 +19,12 @@ class I3DFeatureExtractor(nn.Module):
     REPO_ID = 'flateon/FVD-I3D-torchscript'
     MODEL_FILENAME = 'i3d_torchscript.pt'
 
-    def __init__(self,
-                 device: str = 'cuda',
-                 cache_dir: str | Path | None = None):
+    def __init__(self, device: str = 'cuda', cache_dir: str | Path | None = None):
         super().__init__()
 
         self.device_str = device
         if device == 'cuda' and not torch.cuda.is_available():
-            print(
-                "Warning: CUDA requested but not available – falling back to CPU"
-            )
+            print("Warning: CUDA requested but not available – falling back to CPU")
             self.device = torch.device('cpu')
         else:
             self.device = torch.device(device)
@@ -51,9 +47,7 @@ class I3DFeatureExtractor(nn.Module):
 
         try:
             # Download model from Hugging Face Hub
-            model_path = hf_hub_download(repo_id=self.REPO_ID,
-                                         filename=self.MODEL_FILENAME,
-                                         cache_dir=self.cache_dir)
+            model_path = hf_hub_download(repo_id=self.REPO_ID, filename=self.MODEL_FILENAME, cache_dir=self.cache_dir)
 
             # Load directly to chosen device
             model = torch.jit.load(model_path, map_location=self.device)
@@ -61,10 +55,9 @@ class I3DFeatureExtractor(nn.Module):
             return model
 
         except Exception as e:
-            raise RuntimeError(
-                f"Failed to load I3D model from Hugging Face Hub. Error: {e}\n"
-                f"Ensure you have internet connection and huggingface_hub installed:\n"
-                f"pip install huggingface_hub") from e
+            raise RuntimeError(f"Failed to load I3D model from Hugging Face Hub. Error: {e}\n"
+                               f"Ensure you have internet connection and huggingface_hub installed:\n"
+                               f"uv pip install huggingface_hub") from e
 
     def preprocess(self, videos: torch.Tensor) -> torch.Tensor:
         """
@@ -88,10 +81,7 @@ class I3DFeatureExtractor(nn.Module):
         # Resize to 224x224 if needed
         if H != 224 or W != 224:
             videos = videos.reshape(B * T, C, H, W)
-            videos = F.interpolate(videos,
-                                   size=(224, 224),
-                                   mode='bilinear',
-                                   align_corners=False)
+            videos = F.interpolate(videos, size=(224, 224), mode='bilinear', align_corners=False)
             videos = videos.reshape(B, T, C, 224, 224)
 
         # Convert to [B, C, T, H, W] format
@@ -100,10 +90,7 @@ class I3DFeatureExtractor(nn.Module):
         return videos
 
     @torch.no_grad()
-    def extract_features(self,
-                         videos: torch.Tensor,
-                         batch_size: int = 32,
-                         verbose: bool = True) -> torch.Tensor:
+    def extract_features(self, videos: torch.Tensor, batch_size: int = 32, verbose: bool = True) -> torch.Tensor:
         """
         Extract I3D features
         
@@ -127,16 +114,11 @@ class I3DFeatureExtractor(nn.Module):
             batch = self.preprocess(batch)  # Now returns [B, C, T, H, W]
 
             # Use the HF model without rescale/resize (we handle it in preprocess)
-            features = self.model(batch,
-                                  rescale=False,
-                                  resize=False,
-                                  return_features=True)
+            features = self.model(batch, rescale=False, resize=False, return_features=True)
 
             all_features.append(features.cpu())
 
         return torch.cat(all_features, dim=0)
 
-    def __call__(self,
-                 videos: torch.Tensor,
-                 batch_size: int = 32) -> torch.Tensor:
+    def __call__(self, videos: torch.Tensor, batch_size: int = 32) -> torch.Tensor:
         return self.extract_features(videos, batch_size=batch_size)

benchmarks/fvd/run_fvd.py

@@ -36,10 +36,7 @@ def main() -> None:
                 cache_real_features=str(script_dir / f'fvd-cache/{model_name}'),
             )
 
-            results = compute_fvd_with_config(real_dir,
-                                              gen_dir,
-                                              cfg,
-                                              verbose=False)
+            results = compute_fvd_with_config(real_dir, gen_dir, cfg, verbose=False)
             print(f"FVD: {results['fvd']}\nModel: {results['model']}")
 
         except Exception as e:

benchmarks/fvd/validate_fvd.py

@@ -59,10 +59,7 @@ def validate_fvd(subset_a: Path, subset_b: Path, num_videos: int):
     print("TEST 1: Identity Test")
     print("=" * 70)
 
-    result1 = compute_fvd_with_config(real_videos=str(subset_a),
-                                      gen_videos=str(subset_a),
-                                      config=config,
-                                      verbose=False)
+    result1 = compute_fvd_with_config(real_videos=str(subset_a), gen_videos=str(subset_a), config=config, verbose=False)
     fvd_identity = result1['fvd']
     print(f"\nIdentity FVD: {fvd_identity:.2f}")
 
@@ -70,10 +67,7 @@ def validate_fvd(subset_a: Path, subset_b: Path, num_videos: int):
     print("TEST 2: Real vs Real")
     print("=" * 70)
 
-    result2 = compute_fvd_with_config(real_videos=str(subset_a),
-                                      gen_videos=str(subset_b),
-                                      config=config,
-                                      verbose=False)
+    result2 = compute_fvd_with_config(real_videos=str(subset_a), gen_videos=str(subset_b), config=config, verbose=False)
     fvd_real = result2['fvd']
     print(f"\nReal vs Real FVD: {fvd_real:.2f}")
 
@@ -87,9 +81,7 @@ def validate_fvd(subset_a: Path, subset_b: Path, num_videos: int):
 def main() -> None:
     bair_dir = Path('benchmarks/data/bair_full_videos')
 
-    subset_a, subset_b, count = split_videos(bair_dir,
-                                             n_per_subset=128,
-                                             seed=42)
+    subset_a, subset_b, count = split_videos(bair_dir, n_per_subset=128, seed=42)
     validate_fvd(subset_a, subset_b, count)
 
 

benchmarks/fvd/video_utils.py

@@ -54,8 +54,7 @@ def _load_video_cv2(video_path: str | Path,
             raise RuntimeError(f"Video has 0 frames: {video_path}")
 
         frames = np.stack(frames)  # [T, H, W, C]
-        frames = torch.from_numpy(frames).permute(0, 3, 1,
-                                                  2).float()  # [T, C, H, W]
+        frames = torch.from_numpy(frames).permute(0, 3, 1, 2).float()  # [T, C, H, W]
         return frames
 
     if total_frames == 0:
@@ -63,14 +62,11 @@ def _load_video_cv2(video_path: str | Path,
 
     # Determine frame indices for sampling
     if total_frames < num_frames:
-        frame_indices = list(range(
-            total_frames)) + [total_frames - 1] * (num_frames - total_frames)
+        frame_indices = list(range(total_frames)) + [total_frames - 1] * (num_frames - total_frames)
     elif sample_strategy == 'uniform':
-        frame_indices = np.linspace(0, total_frames - 1, num_frames,
-                                    dtype=int).tolist()
+        frame_indices = np.linspace(0, total_frames - 1, num_frames, dtype=int).tolist()
     elif sample_strategy == 'random':
-        frame_indices = sorted(
-            np.random.choice(total_frames, num_frames, replace=False))
+        frame_indices = sorted(np.random.choice(total_frames, num_frames, replace=False))
     else:
         raise ValueError(f"Unknown sample_strategy: {sample_strategy}")
 
@@ -94,17 +90,15 @@ def _load_video_cv2(video_path: str | Path,
     cap.release()
 
     frames = np.stack(frames)  # [T, H, W, C]
-    frames = torch.from_numpy(frames).permute(0, 3, 1,
-                                              2).float()  # [T, C, H, W]
+    frames = torch.from_numpy(frames).permute(0, 3, 1, 2).float()  # [T, C, H, W]
 
     return frames
 
 
-def _load_video_from_frames(
-        frame_dir: str | Path,
-        num_frames: int | None = 16,
-        sample_strategy: str = 'uniform',
-        frame_extensions: list[str] | None = None) -> torch.Tensor:
+def _load_video_from_frames(frame_dir: str | Path,
+                            num_frames: int | None = 16,
+                            sample_strategy: str = 'uniform',
+                            frame_extensions: list[str] | None = None) -> torch.Tensor:
     """
     Load video from directory of frame images.
     
@@ -131,9 +125,7 @@ def _load_video_from_frames(
         frame_files.extend(frame_dir.glob(f"*{ext}"))
 
     if len(frame_files) == 0:
-        raise ValueError(
-            f"No frames found in {frame_dir} with extensions {frame_extensions}"
-        )
+        raise ValueError(f"No frames found in {frame_dir} with extensions {frame_extensions}")
 
     frame_files = sorted(frame_files, key=lambda x: x.name)
     total_frames = len(frame_files)
@@ -143,16 +135,11 @@ def _load_video_from_frames(
         frame_indices = list(range(total_frames))
     else:
         if total_frames < num_frames:
-            frame_indices = list(range(total_frames)) + [total_frames - 1] * (
-                num_frames - total_frames)
+            frame_indices = list(range(total_frames)) + [total_frames - 1] * (num_frames - total_frames)
         elif sample_strategy == 'uniform':
-            frame_indices = np.linspace(0,
-                                        total_frames - 1,
-                                        num_frames,
-                                        dtype=int).tolist()
+            frame_indices = np.linspace(0, total_frames - 1, num_frames, dtype=int).tolist()
         elif sample_strategy == 'random':
-            frame_indices = sorted(
-                np.random.choice(total_frames, num_frames, replace=False))
+            frame_indices = sorted(np.random.choice(total_frames, num_frames, replace=False))
         else:
             raise ValueError(f"Unknown sample_strategy: {sample_strategy}")
 
@@ -170,8 +157,7 @@ def _load_video_from_frames(
 
     # Stack and convert to tensor
     frames = np.stack(frames)  # [T, H, W, C]
-    frames = torch.from_numpy(frames).permute(0, 3, 1,
-                                              2).float()  # [T, C, H, W]
+    frames = torch.from_numpy(frames).permute(0, 3, 1, 2).float()  # [T, C, H, W]
 
     return frames
 
@@ -226,13 +212,12 @@ def load_video_auto(video_path: str | Path,
         raise ValueError(f"Unknown video format at {video_path}")
 
 
-def sample_clips_from_video(
-        video: torch.Tensor,
-        num_frames_per_clip: int = 16,
-        num_clips: int = 1,
-        strategy: str | ClipSamplingStrategy = ClipSamplingStrategy.BEGINNING,
-        frame_stride: int = 1,
-        temporal_stride: int = 1) -> list[torch.Tensor]:
+def sample_clips_from_video(video: torch.Tensor,
+                            num_frames_per_clip: int = 16,
+                            num_clips: int = 1,
+                            strategy: str | ClipSamplingStrategy = ClipSamplingStrategy.BEGINNING,
+                            frame_stride: int = 1,
+                            temporal_stride: int = 1) -> list[torch.Tensor]:
     """
     Sample clips from a video with various strategies.
         
@@ -296,10 +281,7 @@ def sample_clips_from_video(
     elif strategy == ClipSamplingStrategy.RANDOM:
         # Sample N random clips
         for _ in range(num_clips):
-            if effective_clip_length == T:
-                start = 0
-            else:
-                start = np.random.randint(0, T - effective_clip_length + 1)
+            start = 0 if effective_clip_length == T else np.random.randint(0, T - effective_clip_length + 1)
             clip = video[start:start + effective_clip_length]
             clips.append(clip)
 
@@ -312,8 +294,7 @@ def sample_clips_from_video(
             clips.append(clip)
         else:
             # Multiple uniformly spaced clips
-            step = (T - effective_clip_length) / (num_clips -
-                                                  1) if num_clips > 1 else 0
+            step = (T - effective_clip_length) / (num_clips - 1) if num_clips > 1 else 0
             for i in range(num_clips):
                 start = int(i * step)
                 start = min(start, T - effective_clip_length)
@@ -422,15 +403,12 @@ def load_video_clips_streaming(directory: str | Path,
     failed_count = 0
     total_clips = 0
 
-    iterator = tqdm(video_paths,
-                    desc="Loading videos") if verbose else video_paths
+    iterator = tqdm(video_paths, desc="Loading videos") if verbose else video_paths
 
     for video_path in iterator:
         try:
             # Load full video
-            video = load_video_auto(video_path,
-                                    num_frames=None,
-                                    sample_strategy='uniform')
+            video = load_video_auto(video_path, num_frames=None, sample_strategy='uniform')
 
             # Sample clips from video
             clips = sample_clips_from_video(video,
@@ -445,18 +423,14 @@ def load_video_clips_streaming(directory: str | Path,
                     T, C, H, W = clip.shape
                     if target_size != (H, W):
                         # Resize to target size
-                        clip = clip.contiguous(
-                        )  # Fix non-contiguous tensors first
-                        clip_flat = clip.view(T * C, H,
-                                              W).unsqueeze(0)  # [1, T*C, H, W]
-                        clip_resized = torch.nn.functional.interpolate(
-                            clip_flat,
-                            size=target_size,
-                            mode='bilinear',
-                            align_corners=False)
-                        clip = clip_resized.squeeze(0).view(
-                            T, C, target_size[0],
-                            target_size[1])  # Back to [T, C, H, W]
+                        clip = clip.contiguous()  # Fix non-contiguous tensors first
+                        clip_flat = clip.view(T * C, H, W).unsqueeze(0)  # [1, T*C, H, W]
+                        clip_resized = torch.nn.functional.interpolate(clip_flat,
+                                                                       size=target_size,
+                                                                       mode='bilinear',
+                                                                       align_corners=False)
+                        clip = clip_resized.squeeze(0).view(T, C, target_size[0],
+                                                            target_size[1])  # Back to [T, C, H, W]
                     resized_clips.append(clip)
                 clips = resized_clips
 
@@ -480,11 +454,7 @@ def load_video_clips_streaming(directory: str | Path,
 
     failure_rate = failed_count / len(video_paths)
     if failure_rate > 0.1:  # More than 10% failed
-        print(
-            f"\nWARNING: {failure_rate:.1%} of videos failed to load ({failed_count}/{len(video_paths)})"
-        )
+        print(f"\nWARNING: {failure_rate:.1%} of videos failed to load ({failed_count}/{len(video_paths)})")
 
     if verbose:
-        print(
-            f"\nSuccessfully loaded {total_clips} clips from {len(video_paths) - failed_count} videos"
-        )
+        print(f"\nSuccessfully loaded {total_clips} clips from {len(video_paths) - failed_count} videos")

benchmarks/scripts/run.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # 1. Install missing dependency
-pip install -q opencv-python-headless transformers huggingface_hub
+uv pip install -q opencv-python-headless transformers huggingface_hub
 
 # 2. Run FVD script
 python benchmarks/fvd/run_fvd.py

benchmarks/scripts/setup_fvd.sh

@@ -1,4 +1,4 @@
 #!/bin/bash
 
 # 1. Install missing dependency
-pip install -q opencv-python-headless
+uv pip install -q opencv-python-headless

collect_env.py

@@ -100,10 +100,7 @@ DEFAULT_PIP_PATTERNS = {
 def run(command):
     """Return (return-code, stdout, stderr)."""
     shell = True if type(command) is str else False
-    p = subprocess.Popen(command,
-                         stdout=subprocess.PIPE,
-                         stderr=subprocess.PIPE,
-                         shell=shell)
+    p = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=shell)
     raw_output, raw_err = p.communicate()
     rc = p.returncode
     if get_platform() == 'win32':
@@ -157,8 +154,7 @@ def get_conda_packages(run_lambda, patterns=None):
         return out
 
     return "\n".join(line for line in out.splitlines()
-                     if not line.startswith("#") and any(name in line
-                                                         for name in patterns))
+                     if not line.startswith("#") and any(name in line for name in patterns))
 
 
 def get_gcc_version(run_lambda):
@@ -166,27 +162,24 @@ def get_gcc_version(run_lambda):
 
 
 def get_clang_version(run_lambda):
-    return run_and_parse_first_match(run_lambda, 'clang --version',
-                                     r'clang version (.*)')
+    return run_and_parse_first_match(run_lambda, 'clang --version', r'clang version (.*)')
 
 
 def get_cmake_version(run_lambda):
-    return run_and_parse_first_match(run_lambda, 'cmake --version',
-                                     r'cmake (.*)')
+    return run_and_parse_first_match(run_lambda, 'cmake --version', r'cmake (.*)')
 
 
 def get_nvidia_driver_version(run_lambda):
     if get_platform() == 'darwin':
         cmd = 'kextstat | grep -i cuda'
-        return run_and_parse_first_match(run_lambda, cmd,
-                                         r'com[.]nvidia[.]CUDA [(](.*?)[)]')
+        return run_and_parse_first_match(run_lambda, cmd, r'com[.]nvidia[.]CUDA [(](.*?)[)]')
     smi = get_nvidia_smi()
     return run_and_parse_first_match(run_lambda, smi, r'Driver Version: (.*?) ')
 
 
 def get_gpu_info(run_lambda):
-    if get_platform() == 'darwin' or (TORCH_AVAILABLE and hasattr(
-            torch.version, 'hip') and torch.version.hip is not None):
+    if get_platform() == 'darwin' or (TORCH_AVAILABLE and hasattr(torch.version, 'hip')
+                                      and torch.version.hip is not None):
         if TORCH_AVAILABLE and torch.cuda.is_available():
             if torch.version.hip is not None:
                 prop = torch.cuda.get_device_properties(0)
@@ -208,8 +201,7 @@ def get_gpu_info(run_lambda):
 
 
 def get_running_cuda_version(run_lambda):
-    return run_and_parse_first_match(run_lambda, 'nvcc --version',
-                                     r'release .+ V(.*)')
+    return run_and_parse_first_match(run_lambda, 'nvcc --version', r'release .+ V(.*)')
 
 
 def get_cudnn_version(run_lambda):
@@ -255,8 +247,7 @@ def get_nvidia_smi():
     if get_platform() == 'win32':
         system_root = os.environ.get('SYSTEMROOT', 'C:\\Windows')
         program_files_root = os.environ.get('PROGRAMFILES', 'C:\\Program Files')
-        legacy_path = os.path.join(program_files_root, 'NVIDIA Corporation',
-                                   'NVSMI', smi)
+        legacy_path = os.path.join(program_files_root, 'NVIDIA Corporation', 'NVSMI', smi)
         new_path = os.path.join(system_root, 'System32', smi)
         smis = [new_path, legacy_path]
         for candidate_smi in smis:
@@ -388,10 +379,8 @@ def get_cpu_info(run_lambda):
     if get_platform() == 'linux':
         rc, out, err = run_lambda('lscpu')
     elif get_platform() == 'win32':
-        rc, out, err = run_lambda(
-            'wmic cpu get Name,Manufacturer,Family,Architecture,ProcessorType,DeviceID, \
-        CurrentClockSpeed,MaxClockSpeed,L2CacheSize,L2CacheSpeed,Revision /VALUE'
-        )
+        rc, out, err = run_lambda('wmic cpu get Name,Manufacturer,Family,Architecture,ProcessorType,DeviceID, \
+        CurrentClockSpeed,MaxClockSpeed,L2CacheSize,L2CacheSpeed,Revision /VALUE')
     elif get_platform() == 'darwin':
         rc, out, err = run_lambda("sysctl -n machdep.cpu.brand_string")
     cpu_info = 'None'
@@ -416,27 +405,22 @@ def get_platform():
 
 
 def get_mac_version(run_lambda):
-    return run_and_parse_first_match(run_lambda, 'sw_vers -productVersion',
-                                     r'(.*)')
+    return run_and_parse_first_match(run_lambda, 'sw_vers -productVersion', r'(.*)')
 
 
 def get_windows_version(run_lambda):
     system_root = os.environ.get('SYSTEMROOT', 'C:\\Windows')
     wmic_cmd = os.path.join(system_root, 'System32', 'Wbem', 'wmic')
     findstr_cmd = os.path.join(system_root, 'System32', 'findstr')
-    return run_and_read_all(
-        run_lambda,
-        '{} os get Caption | {} /v Caption'.format(wmic_cmd, findstr_cmd))
+    return run_and_read_all(run_lambda, '{} os get Caption | {} /v Caption'.format(wmic_cmd, findstr_cmd))
 
 
 def get_lsb_version(run_lambda):
-    return run_and_parse_first_match(run_lambda, 'lsb_release -a',
-                                     r'Description:\t(.*)')
+    return run_and_parse_first_match(run_lambda, 'lsb_release -a', r'Description:\t(.*)')
 
 
 def check_release_file(run_lambda):
-    return run_and_parse_first_match(run_lambda, 'cat /etc/*-release',
-                                     r'PRETTY_NAME="(.*)"')
+    return run_and_parse_first_match(run_lambda, 'cat /etc/*-release', r'PRETTY_NAME="(.*)"')
 
 
 def get_os(run_lambda):
@@ -499,13 +483,10 @@ def get_pip_packages(run_lambda, patterns=None):
         elif shutil.which("uv") is not None:
             cmd = ["uv", "pip", "list", "--format=freeze"]
         else:
-            raise RuntimeError(
-                "Could not collect pip list output (pip or uv module not available)"
-            )
+            raise RuntimeError("Could not collect pip list output (pip or uv module not available)")
 
         out = run_and_read_all(run_lambda, cmd)
-        return "\n".join(line for line in out.splitlines()
-                         if any(name in line for name in patterns))
+        return "\n".join(line for line in out.splitlines() if any(name in line for name in patterns))
 
     pip_version = 'pip3' if sys.version[0] == '3' else 'pip'
     out = run_with_pip()
@@ -537,8 +518,7 @@ def is_xnnpack_available():
 def get_env_vars():
     env_vars = ''
     secret_terms = ('secret', 'token', 'api', 'access', 'password')
-    report_prefix = ("TORCH", "NCCL", "PYTORCH", "CUDA", "CUBLAS", "CUDNN",
-                     "OMP_", "MKL_", "NVIDIA")
+    report_prefix = ("TORCH", "NCCL", "PYTORCH", "CUDA", "CUBLAS", "CUDNN", "OMP_", "MKL_", "NVIDIA")
     for k, v in os.environ.items():
         if any(term in k.lower() for term in secret_terms):
             continue
@@ -559,8 +539,7 @@ def get_env_info():
         debug_mode_str = str(torch.version.debug)
         cuda_available_str = str(torch.cuda.is_available())
         cuda_version_str = torch.version.cuda
-        if not hasattr(torch.version,
-                       'hip') or torch.version.hip is None:  # cuda version
+        if not hasattr(torch.version, 'hip') or torch.version.hip is None:  # cuda version
             hip_compiled_version = hip_runtime_version = miopen_runtime_version = 'N/A'
         else:  # HIP version
 
@@ -588,9 +567,8 @@ def get_env_info():
     return SystemEnv(
         torch_version=version_str,
         is_debug_build=debug_mode_str,
-        python_version='{} ({}-bit runtime)'.format(
-            sys_version,
-            sys.maxsize.bit_length() + 1),
+        python_version='{} ({}-bit runtime)'.format(sys_version,
+                                                    sys.maxsize.bit_length() + 1),
         python_platform=get_python_platform(),
         is_cuda_available=cuda_available_str,
         cuda_compiled_version=cuda_version_str,
@@ -714,10 +692,8 @@ def pretty_str(envinfo):
         'nvidia_driver_version',
     ]
     all_cuda_fields = dynamic_cuda_fields + ['cudnn_version']
-    all_dynamic_cuda_fields_missing = all(mutable_dict[field] is None
-                                          for field in dynamic_cuda_fields)
-    if TORCH_AVAILABLE and not torch.cuda.is_available(
-    ) and all_dynamic_cuda_fields_missing:
+    all_dynamic_cuda_fields_missing = all(mutable_dict[field] is None for field in dynamic_cuda_fields)
+    if TORCH_AVAILABLE and not torch.cuda.is_available() and all_dynamic_cuda_fields_missing:
         for field in all_cuda_fields:
             mutable_dict[field] = 'No CUDA'
         if envinfo.cuda_compiled_version is None:
@@ -730,19 +706,15 @@ def pretty_str(envinfo):
     mutable_dict = replace_nones(mutable_dict)
 
     # If either of these are '', replace with 'No relevant packages'
-    mutable_dict['pip_packages'] = replace_if_empty(
-        mutable_dict['pip_packages'])
-    mutable_dict['conda_packages'] = replace_if_empty(
-        mutable_dict['conda_packages'])
+    mutable_dict['pip_packages'] = replace_if_empty(mutable_dict['pip_packages'])
+    mutable_dict['conda_packages'] = replace_if_empty(mutable_dict['conda_packages'])
 
     # Tag conda and pip packages with a prefix
     # If they were previously None, they'll show up as ie '[conda] Could not collect'
     if mutable_dict['pip_packages']:
-        mutable_dict['pip_packages'] = prepend(
-            mutable_dict['pip_packages'], '[{}] '.format(envinfo.pip_version))
+        mutable_dict['pip_packages'] = prepend(mutable_dict['pip_packages'], '[{}] '.format(envinfo.pip_version))
     if mutable_dict['conda_packages']:
-        mutable_dict['conda_packages'] = prepend(mutable_dict['conda_packages'],
-                                                 '[conda] ')
+        mutable_dict['conda_packages'] = prepend(mutable_dict['conda_packages'], '[conda] ')
     mutable_dict['cpu_info'] = envinfo.cpu_info
     return env_info_fmt.format(**mutable_dict)
 
@@ -756,18 +728,13 @@ def main():
     output = get_pretty_env_info()
     print(output)
 
-    if TORCH_AVAILABLE and hasattr(torch, 'utils') and hasattr(
-            torch.utils, '_crash_handler'):
+    if TORCH_AVAILABLE and hasattr(torch, 'utils') and hasattr(torch.utils, '_crash_handler'):
         minidump_dir = torch.utils._crash_handler.DEFAULT_MINIDUMP_DIR
         if sys.platform == "linux" and os.path.exists(minidump_dir):
-            dumps = [
-                os.path.join(minidump_dir, dump)
-                for dump in os.listdir(minidump_dir)
-            ]
+            dumps = [os.path.join(minidump_dir, dump) for dump in os.listdir(minidump_dir)]
             latest = max(dumps, key=os.path.getctime)
             ctime = os.path.getctime(latest)
-            creation_time = datetime.datetime.fromtimestamp(ctime).strftime(
-                '%Y-%m-%d %H:%M:%S')
+            creation_time = datetime.datetime.fromtimestamp(ctime).strftime('%Y-%m-%d %H:%M:%S')
             msg = "\n*** Detected a minidump at {} created on {}, ".format(latest, creation_time) + \
                   "if this is related to your bug please include it when you file a report ***"
             print(msg, file=sys.stderr)

comfyui/README.md

@@ -38,10 +38,10 @@ cp -r /path/to/FastVideo/comfyui /path/to/ComfyUI/custom_nodes/FastVideo
 
 #### Install dependencies:
 
-Currently, the only dependency is `fastvideo`, which can be installed using pip.
+Currently, the only dependency is `fastvideo`, which can be installed with `uv`.
 
 ```bash
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 #### Install missing custom nodes:

comfyui/__init__.py

@@ -1,5 +1,4 @@
-from .video_generator.nodes import (NODE_CLASS_MAPPINGS,
-                                    NODE_DISPLAY_NAME_MAPPINGS)
+from .video_generator.nodes import (NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS)
 
 WEB_DIRECTORY = "./web"
-__all__ = ['NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS', 'WEB_DIRECTORY']
+__all__ = ['NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS', 'WEB_DIRECTORY']

comfyui/video_generator/load_image.py

@@ -14,10 +14,7 @@ class LoadImagePath:
     @classmethod
     def INPUT_TYPES(s):
         input_dir = folder_paths.get_input_directory()
-        files = [
-            f for f in os.listdir(input_dir)
-            if os.path.isfile(os.path.join(input_dir, f))
-        ]
+        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
         files = folder_paths.filter_files_content_types(files, ["image"])
         return {
             "required": {
@@ -65,13 +62,10 @@ class LoadImagePath:
                 None,
             ]
             if 'A' in processed_image.getbands():
-                mask = np.array(processed_image.getchannel('A')).astype(
-                    np.float32) / 255.0
+                mask = np.array(processed_image.getchannel('A')).astype(np.float32) / 255.0
                 mask = 1. - torch.from_numpy(mask)
             elif processed_image.mode == 'P' and 'transparency' in processed_image.info:
-                mask = np.array(
-                    processed_image.convert('RGBA').getchannel('A')).astype(
-                        np.float32) / 255.0
+                mask = np.array(processed_image.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
                 mask = 1. - torch.from_numpy(mask)
             else:
                 mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")

comfyui/video_generator/node_helpers.py

@@ -9,8 +9,7 @@ from PIL import ImageFile, UnidentifiedImageError
 T = TypeVar('T')
 
 
-def conditioning_set_values(conditioning: list[Any],
-                            values: dict[str, Any] | None = None) -> list[Any]:
+def conditioning_set_values(conditioning: list[Any], values: dict[str, Any] | None = None) -> list[Any]:
     if values is None:
         values = {}
     c = []
@@ -27,8 +26,7 @@ def pillow(fn: Callable[[Any], T], arg: Any) -> T:
     prev_value = None
     try:
         x = fn(arg)
-    except (OSError, UnidentifiedImageError, ValueError
-            ):  #PIL issues #4472 and #2445, also fixes ComfyUI issue #3416
+    except (OSError, UnidentifiedImageError, ValueError):  #PIL issues #4472 and #2445, also fixes ComfyUI issue #3416
         prev_value = ImageFile.LOAD_TRUNCATED_IMAGES
         ImageFile.LOAD_TRUNCATED_IMAGES = True
         x = fn(arg)
@@ -39,12 +37,7 @@ def pillow(fn: Callable[[Any], T], arg: Any) -> T:
 
 
 def hasher() -> Callable[[], Any]:
-    hashfuncs = {
-        "md5": hashlib.md5,
-        "sha1": hashlib.sha1,
-        "sha256": hashlib.sha256,
-        "sha512": hashlib.sha512
-    }
+    hashfuncs = {"md5": hashlib.md5, "sha1": hashlib.sha1, "sha256": hashlib.sha256, "sha512": hashlib.sha512}
     return hashfuncs[args.default_hashing_function]
 
 
@@ -58,8 +51,7 @@ def string_to_torch_dtype(string: str) -> torch.dtype | None:
     return None
 
 
-def image_alpha_fix(destination: torch.Tensor,
-                    source: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
+def image_alpha_fix(destination: torch.Tensor, source: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
     if destination.shape[-1] < source.shape[-1]:
         source = source[..., :destination.shape[-1]]
     elif destination.shape[-1] > source.shape[-1]:

comfyui/video_generator/text_encoder_config.py

@@ -26,11 +26,7 @@ class TextEncoderConfig:
     CATEGORY = "fastvideo"
 
     def set_args(self, prefix, quant_config, lora_config):
-        raw_args = {
-            "prefix": prefix,
-            "quant_config": quant_config,
-            "lora_config": lora_config
-        }
+        raw_args = {"prefix": prefix, "quant_config": quant_config, "lora_config": lora_config}
 
         # Filter out keys where value is -99999
         args = {k: v for k, v in raw_args.items() if str(int(v)) != str(-99999)}

comfyui/video_generator/video_generator.py

@@ -13,11 +13,7 @@ from comfy.model_management import processing_interrupted
 from fastvideo import PipelineConfig
 from fastvideo import VideoGenerator as FastVideoGenerator
 
-sys.path.insert(
-    0,
-    os.path.dirname(
-        os.path.dirname(
-            os.path.dirname(os.path.dirname(os.path.abspath(__file__))))))
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))))
 
 
 # Custom exception for interruption
@@ -28,8 +24,7 @@ class GenerationInterruptedException(Exception):
 # Custom exception for interruption that ComfyUI will recognize
 class GenerationCancelledException(Exception):
 
-    def __init__(self,
-                 message: str = "Generation was cancelled by user") -> None:
+    def __init__(self, message: str = "Generation was cancelled by user") -> None:
         self.message = message
         super().__init__(self.message)
 
@@ -139,8 +134,7 @@ class VideoGenerator:
                 self._generation_interrupted = True
 
                 # Try to send interrupt signal to worker processes
-                if self.generator is not None and hasattr(
-                        self.generator, 'executor'):
+                if self.generator is not None and hasattr(self.generator, 'executor'):
                     try:
                         # The MultiprocExecutor has a workers attribute
                         if hasattr(self.generator.executor, 'workers'):
@@ -156,16 +150,12 @@ class VideoGenerator:
                 break
             time.sleep(0.5)
 
-    def _run_generation(self, prompt: str, output_path: str,
-                        inference_args: dict[str, Any]) -> None:
+    def _run_generation(self, prompt: str, output_path: str, inference_args: dict[str, Any]) -> None:
         """Thread function to run the generation"""
         try:
             if self.generator is not None:
-                self.generator.generate_video(prompt=prompt,
-                                              output_path=output_path,
-                                              **inference_args)
-                self._generation_result = os.path.join(output_path,
-                                                       f"{prompt[:100]}.mp4")
+                self.generator.generate_video(prompt=prompt, output_path=output_path, **inference_args)
+                self._generation_result = os.path.join(output_path, f"{prompt[:100]}.mp4")
             else:
                 raise RuntimeError("Generator is not initialized")
         except Exception as e:
@@ -226,8 +216,7 @@ class VideoGenerator:
             update_config_from_args(pipeline_config.vae_config, vae_config)
 
         if text_encoder_config is not None:
-            update_config_from_args(pipeline_config.text_encoder_configs,
-                                    text_encoder_config)
+            update_config_from_args(pipeline_config.text_encoder_configs, text_encoder_config)
 
         # Update top-level pipeline config with remaining arguments
         raw_pipeline_args = {}
@@ -245,10 +234,7 @@ class VideoGenerator:
             raw_pipeline_args['text_encoder_precision'] = text_encoder_precision
 
         # Filter out any value explicitly set to -99999 (auto values)
-        pipeline_args = {
-            k: v
-            for k, v in raw_pipeline_args.items() if str(int(v)) != str(-99999)
-        }
+        pipeline_args = {k: v for k, v in raw_pipeline_args.items() if str(int(v)) != str(-99999)}
 
         update_config_from_args(pipeline_config, pipeline_args)
 
@@ -262,38 +248,30 @@ class VideoGenerator:
         if dit_cpu_offload is not None:
             raw_generation_args['dit_cpu_offload'] = dit_cpu_offload
 
-        generation_args = {
-            k: v
-            for k, v in raw_generation_args.items()
-            if str(int(v)) != str(-99999)
-        }
+        generation_args = {k: v for k, v in raw_generation_args.items() if str(int(v)) != str(-99999)}
 
         if self.generator is None:
             print('generation_args', generation_args)
             print('pipeline_config', pipeline_config)
-            self.generator = FastVideoGenerator.from_pretrained(
-                model_path=model_path,
-                **generation_args,
-                pipeline_config=pipeline_config)
+            self.generator = FastVideoGenerator.from_pretrained(model_path=model_path,
+                                                                **generation_args,
+                                                                pipeline_config=pipeline_config)
 
         print('inference_args', inference_args)
 
         # Start a thread to run the generation
         self._generation_thread = threading.Thread(target=self._run_generation,
-                                                   args=(prompt, output_path,
-                                                         inference_args),
+                                                   args=(prompt, output_path, inference_args),
                                                    daemon=True)
         self._generation_thread.start()
 
         # Start a background thread to monitor for interruptions
         self._generation_active = True
-        self._interrupt_thread = threading.Thread(
-            target=self._monitor_for_interruption, daemon=True)
+        self._interrupt_thread = threading.Thread(target=self._monitor_for_interruption, daemon=True)
         self._interrupt_thread.start()
 
         # Wait for either completion or interruption
-        while self._generation_thread.is_alive(
-        ) and not self._interrupt_event.is_set():
+        while self._generation_thread.is_alive() and not self._interrupt_event.is_set():
             self._generation_thread.join(timeout=0.5)
 
         self._generation_active = False

docker/Dockerfile.python3.10

@@ -42,15 +42,15 @@ RUN source $HOME/.local/bin/env && \
     uv venv --python 3.10 --seed /opt/venv && \
     source /opt/venv/bin/activate && \
     uv pip install --no-cache-dir --upgrade pip && \
-    uv pip install --no-cache-dir .[dev] && \
-    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.10-cp310-cp310-linux_x86_64.whl
+    uv pip install --no-cache-dir ".[dev]" && \
+    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.9.4/flash_attn-2.8.3+cu128torch2.11-cp310-cp310-linux_x86_64.whl
 
 COPY . .
 
 # Install dependencies using uv and set up shell configuration
 RUN source $HOME/.local/bin/env && \
     source /opt/venv/bin/activate && \
-    uv pip install --no-cache-dir -e .[dev] && \
+    uv pip install --no-cache-dir -e ".[dev]" && \
     git config --unset-all http.https://github.com/.extraheader || true && \
     echo 'source /opt/venv/bin/activate' >> /root/.bashrc && \
     echo 'if [ -n "$ZSH_VERSION" ] && [ -f ~/.zshrc ]; then . ~/.zshrc; elif [ -f ~/.bashrc ]; then . ~/.bashrc; fi' > /root/.profile

docker/Dockerfile.python3.11

@@ -42,15 +42,15 @@ RUN source $HOME/.local/bin/env && \
     uv venv --python 3.11 --seed /opt/venv && \
     source /opt/venv/bin/activate && \
     uv pip install --no-cache-dir --upgrade pip && \
-    uv pip install --no-cache-dir .[dev] && \
-    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.10-cp311-cp311-linux_x86_64.whl
+    uv pip install --no-cache-dir ".[dev]" && \
+    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.9.4/flash_attn-2.8.3+cu128torch2.11-cp311-cp311-linux_x86_64.whl
 
 COPY . .
 
 # Install dependencies using uv and set up shell configuration
 RUN source $HOME/.local/bin/env && \
     source /opt/venv/bin/activate && \
-    uv pip install --no-cache-dir -e .[dev] && \
+    uv pip install --no-cache-dir -e ".[dev]" && \
     git config --unset-all http.https://github.com/.extraheader || true && \
     echo 'source /opt/venv/bin/activate' >> /root/.bashrc && \
     echo 'if [ -n "$ZSH_VERSION" ] && [ -f ~/.zshrc ]; then . ~/.zshrc; elif [ -f ~/.bashrc ]; then . ~/.bashrc; fi' > /root/.profile

docker/Dockerfile.python3.12

@@ -42,15 +42,15 @@ RUN source $HOME/.local/bin/env && \
     uv venv --python 3.12 --seed /opt/venv && \
     source /opt/venv/bin/activate && \
     uv pip install --no-cache-dir --upgrade pip && \
-    uv pip install --no-cache-dir .[dev] && \
-    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.10-cp312-cp312-linux_x86_64.whl
+    uv pip install --no-cache-dir ".[dev]" && \
+    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.9.4/flash_attn-2.8.3+cu128torch2.11-cp312-cp312-linux_x86_64.whl
 
 COPY . .
 
 # Install dependencies using uv and set up shell configuration
 RUN source $HOME/.local/bin/env && \
     source /opt/venv/bin/activate && \
-    uv pip install --no-cache-dir -e .[dev] && \
+    uv pip install --no-cache-dir -e ".[dev]" && \
     git config --unset-all http.https://github.com/.extraheader || true && \
     echo 'source /opt/venv/bin/activate' >> /root/.bashrc && \
     echo 'if [ -n "$ZSH_VERSION" ] && [ -f ~/.zshrc ]; then . ~/.zshrc; elif [ -f ~/.bashrc ]; then . ~/.bashrc; fi' > /root/.profile

docker/Dockerfile.python3.12.cuda12.9.1

@@ -42,7 +42,7 @@ RUN source $HOME/.local/bin/env && \
     uv venv --python 3.12 --seed /opt/venv && \
     source /opt/venv/bin/activate && \
     uv pip install --no-cache-dir --upgrade pip && \
-    uv pip install --no-cache-dir .[dev] && \
+    uv pip install --no-cache-dir ".[dev]" && \
     uv pip install --no-cache-dir flash-attn==2.8.3 --no-build-isolation
 
 COPY . .
@@ -50,7 +50,7 @@ COPY . .
 # Install dependencies using uv and set up shell configuration
 RUN source $HOME/.local/bin/env && \
     source /opt/venv/bin/activate && \
-    uv pip install --no-cache-dir -e .[dev] && \
+    uv pip install --no-cache-dir -e ".[dev]" && \
     git config --unset-all http.https://github.com/.extraheader || true && \
     echo 'source /opt/venv/bin/activate' >> /root/.bashrc && \
     echo 'if [ -n "$ZSH_VERSION" ] && [ -f ~/.zshrc ]; then . ~/.zshrc; elif [ -f ~/.bashrc ]; then . ~/.bashrc; fi' > /root/.profile

docker/rocm7_1.Dockerfile

@@ -43,7 +43,7 @@ COPY . .
 # Install dependencies using uv and set up shell configuration
 RUN source $HOME/.local/bin/env && \
     source /opt/venv/bin/activate && \
-    uv pip install --no-cache-dir -e .[rocm] && \
+    uv pip install --no-cache-dir -e ".[rocm]" && \
     git config --unset-all http.https://github.com/.extraheader || true && \
     echo 'source /opt/venv/bin/activate' >> /root/.bashrc && \
     echo 'if [ -n "$ZSH_VERSION" ] && [ -f ~/.zshrc ]; then . ~/.zshrc; elif [ -f ~/.bashrc ]; then . ~/.bashrc; fi' > /root/.profile

docs/README.md

@@ -6,7 +6,7 @@ This directory contains the FastVideo documentation built with MkDocs.
 
 ```bash
 # Install dependencies
-pip install -r requirements-mkdocs.txt
+uv pip install -r requirements-mkdocs.txt
 
 # Serve docs with live reload (recommended for development)
 mkdocs serve
@@ -36,4 +36,4 @@ Then open your browser to: http://localhost:8000
 
 ## Automatic Deployment
 
-Documentation is automatically built and deployed to GitHub Pages when changes are pushed to the `main` branch via the `.github/workflows/docs.yml` workflow.
+Documentation is automatically built and deployed to GitHub Pages when changes are pushed to the `main` branch via the `.github/workflows/infra-docs.yml` workflow.

docs/api/fastvideo.md

@@ -62,9 +62,9 @@ This page contains the complete API reference for the FastVideo library.
       show_root_toc_entry: true
       heading_level: 4
 
-#### fastvideo.configs.sample
+#### fastvideo.api.sampling_param
 
-::: fastvideo.configs.sample
+::: fastvideo.api.sampling_param
     options:
       show_source: true
       show_root_heading: true

docs/contributing/activation_trace.md

@@ -0,0 +1,210 @@
+# Activation Trace Mode
+
+!!! note
+    This page covers Extension 0 (module forward hooks), which is the implemented
+    tracing mechanism. Extensions 1-3 are design sketches for future work and are
+    **not yet implemented**.
+
+## Overview
+
+Activation trace mode is a zero-overhead-when-off, env-gated mechanism for
+dumping per-layer activation statistics during FastVideo inference. Its primary
+use case is **parity debugging across model ports**: enable tracing on both
+FastVideo and the upstream reference implementation, then `diff` the resulting
+JSONL files to find the first divergent layer.
+
+The mechanism is intentionally narrow. It doesn't replace general logging,
+profiling, or function tracing. It answers one question: "at which layer do
+FastVideo and the reference model first produce different numbers?"
+
+## When to use
+
+- Investigating numerical drift between FastVideo and an upstream reference.
+- Debugging mid-pipeline divergence (e.g., one block produces wrong output while earlier blocks match).
+- Validating that a refactor preserves bf16 noise-floor behavior across many layers.
+
+## When NOT to use
+
+| Goal | Use instead |
+|---|---|
+| General logging | `init_logger(__name__)` |
+| Per-stage timing | `FASTVIDEO_STAGE_LOGGING` |
+| Profiling kernel timings | `FASTVIDEO_TORCH_PROFILER_DIR` (see [Profiling](profiling.md)) |
+| Function-call tracing | `FASTVIDEO_TRACE_FUNCTION` (heavy) |
+
+## Quickstart
+
+```bash
+FASTVIDEO_TRACE_ACTIVATIONS=1 \
+FASTVIDEO_TRACE_LAYERS="^block\.layers\.[0-9]+$" \
+FASTVIDEO_TRACE_STATS="abs_mean,sum,max,shape" \
+FASTVIDEO_TRACE_OUTPUT="/tmp/fv_trace.jsonl" \
+python examples/inference/basic/basic_magi_human.py
+```
+
+Each line in `/tmp/fv_trace.jsonl` is a JSON record:
+
+```json
+{"module": "block.layers.0", "tensor": "out", "step": 0, "abs_mean": 1.234, "sum": -5.678, "max": 9.012, "shape": [1, 4096, 5120]}
+```
+
+## Configuration
+
+| Env var | Default | Description |
+|---|---|---|
+| `FASTVIDEO_TRACE_ACTIVATIONS` | `False` | Master toggle. When unset or false, **zero overhead** in the production hot path. |
+| `FASTVIDEO_TRACE_LAYERS` | `""` (all) | Python regex filter applied to `model.named_modules()` names. Empty string matches all modules. |
+| `FASTVIDEO_TRACE_STATS` | `"abs_mean,sum"` | Comma-separated stats to compute. Available: `abs_mean`, `sum`, `min`, `max`, `mean`, `std`, `shape`, `dtype`. |
+| `FASTVIDEO_TRACE_OUTPUT` | `"/tmp/fv_trace_<pid>.jsonl"` | Output file path. `<pid>` is replaced with the process ID at runtime. |
+| `FASTVIDEO_TRACE_STEPS` | `""` (all) | Comma-separated denoising step indices to capture. Empty string captures all steps. |
+
+## Workflow: parity-debug a model port
+
+1. Set up a tightly-controlled comparison: a parity test or a small standalone
+   script that loads both the FastVideo model and the upstream reference with
+   identical inputs and seeds.
+
+2. Run the FastVideo side with tracing on:
+
+   ```bash
+   FASTVIDEO_TRACE_ACTIVATIONS=1 \
+   FASTVIDEO_TRACE_LAYERS="<your regex>" \
+   FASTVIDEO_TRACE_OUTPUT="/tmp/fv_trace_fv.jsonl" \
+   python <fv_runner.py>
+   ```
+
+3. Run the upstream side. The upstream repo needs separate instrumentation. See
+   "Hooking the upstream side" below.
+
+4. Sort both files by `(module, step)` if needed, then diff:
+
+   ```bash
+   diff /tmp/fv_trace_fv.jsonl /tmp/fv_trace_upstream.jsonl
+   ```
+
+5. The first divergent line identifies the first layer where FastVideo and the
+   upstream produce different outputs. Start debugging there.
+
+## Architecture (Extension 0: module forward hooks)
+
+At pipeline initialization, `attach_activation_trace()` reads the env vars once.
+If `FASTVIDEO_TRACE_ACTIVATIONS` is unset or false, the function returns
+immediately and no hooks are registered. If tracing is on, it walks
+`model.named_modules()`, filters by the layer regex, and registers an
+`ActivationStatHook` on each matching module.
+
+During the forward pass, each hook fires after its module completes, computes
+the requested stats on the output tensor, and appends a JSON record to the
+output file.
+
+```
+ComposedPipelineBase
+  └─ attach_activation_trace()
+       ├─ reads env vars (once at startup)
+       ├─ if off: returns None immediately
+       └─ if on: walks named_modules()
+            └─ registers ActivationStatHook on matching modules
+                 └─ on each forward: compute stats → append JSONL
+```
+
+### Zero-overhead-when-off guarantee
+
+- The env var check happens **once at startup** inside `attach_activation_trace()`.
+- If the env var is unset or false, the function returns `None` immediately.
+- No hooks are registered. No branches are added to the production forward path.
+- The only cost when tracing is off is one env var lookup at pipeline
+  initialization, which takes under a microsecond.
+
+### Hooking the upstream side
+
+The upstream reference repo isn't part of FastVideo, so it can't read FastVideo
+env vars directly. Two options:
+
+**Option 1: Inline patch** in your local clone of the upstream repo. Add
+`register_forward_hook` calls in the same shape as `ActivationStatHook`. Clean
+up afterward with `git stash` or `git checkout HEAD -- <file>`.
+
+**Option 2: Wrapper script**. Write a small Python harness that imports the
+upstream model, walks its `named_modules()`, and attaches hooks externally.
+This is the same pattern used in
+`tests/local_tests/transformers/_debug_magi_human_block_parity.py`.
+
+The `add-model-trace` skill at `~/.config/opencode/skill/add-model-trace/`
+provides a script template for this purpose.
+
+## Future extensions (design only, not yet implemented)
+
+### Extension 1: FX/Dynamo backend graph rewrite
+
+**Granularity**: per-FX-node (every matmul, every add).
+
+**Mechanism**: a `torch.compile` backend that takes the captured `GraphModule`
+and inserts logger nodes after each op. Compiles into a separate artifact from
+the production graph.
+
+**Off semantics**: zero overhead. The production compile path is untouched.
+
+**When to add**: if you need to trace inside a `torch.compile`'d graph and
+Extension 0 is too coarse.
+
+**Build cost**: roughly 1-2 days. Reference:
+`torchao.quantization.pt2e._numeric_debugger`.
+
+### Extension 2: AST source injection at import time
+
+**Granularity**: per-line (between any two Python statements).
+
+**Mechanism**: an importlib loader hook rewrites Python source AST at module
+import time, inserting `if TRACE: dump(...)` statements. The decision is made
+once at import.
+
+**Off semantics**: zero overhead. If the env var is off at import time, source
+is loaded as-is.
+
+**When to add**: if you need per-line granularity that even FX-node-level can't
+provide. This is almost never the right choice.
+
+**Build cost**: roughly 1 week. Brittle and hard to debug.
+
+### Extension 3: `__torch_dispatch__` / `TorchDispatchMode`
+
+**Granularity**: per-op (every dispatcher call: matmul, add, view, etc.).
+
+**Mechanism**: a `TorchDispatchMode` context manager that intercepts all ops at
+the dispatcher level.
+
+**Off semantics**: zero overhead. PyTorch's dispatcher only invokes mode hooks
+when a mode is active.
+
+**When on**: significant overhead. Every op pays a Python callback cost. Triton
+kernels bypass it.
+
+**When to add**: useful for quantization or dtype debugging where module-level
+granularity isn't enough.
+
+**Build cost**: roughly 1 day. Reference:
+`torch.utils._python_dispatch.TorchDispatchMode`.
+
+## Comparison with similar tools
+
+| Tool | Pattern | FastVideo equivalent |
+|---|---|---|
+| SGLang `--debug-tensor-dump-output-folder` | env-gated forward hooks at startup | Extension 0 (this) |
+| TransformerEngine `DumpTensors` | config-driven selective dumps | Extension 0 (env-driven) |
+| HuggingFace `output_hidden_states=True` | source-level boolean gating | Not used; Extension 0 avoids model code edits |
+| torchao numeric debugger | FX pass + node-level loggers | Extension 1 (future) |
+| W&B `wandb.watch()` | runtime forward hooks (always on once registered) | Extension 0 has a similar mechanism, but gated off by default |
+
+## Implementation references
+
+- Module: `fastvideo/hooks/activation_trace.py`
+- Env vars: `fastvideo/envs.py` (`FASTVIDEO_TRACE_ACTIVATIONS` and friends)
+- Pipeline integration: `fastvideo/pipelines/composed_pipeline_base.py`
+- Tests: `fastvideo/tests/hooks/test_activation_trace.py`
+- Companion skill (for ad-hoc port investigations): `~/.config/opencode/skill/add-model-trace/`
+
+## Changelog
+
+| Date | Change |
+|---|---|
+| 2026-05-01 | Initial Extension 0 (module forward hooks) implementation. Extensions 1-3 designed but not implemented. |

docs/contributing/ci_architecture.md

@@ -0,0 +1,331 @@
+# CI Architecture
+
+## Overview
+
+FastVideo uses a three-tier CI pipeline designed to keep feedback fast on every push while
+protecting `main` through a full GPU regression suite before any merge.
+
+```
+PR push
+  │
+  ├─► Tier 1: Pre-commit (~2 min)
+  │     GitHub Actions / ubuntu-latest
+  │     yapf, ruff, mypy, codespell, pymarkdown, actionlint, check-filenames
+  │
+  └─► Tier 2: Fastcheck (~10-20 min, path-filtered)
+        Buildkite / Modal GPU instances
+        Only runs tests for paths you changed
+
+              │ (developer comments /merge or maintainer adds 'ready' label)
+              ▼
+        Tier 3: Full Suite (~60-90 min)
+          Buildkite / Modal GPU instances
+          All integration, SSIM, training, and performance tests
+          Runs on the PR branch directly
+              │
+          pass ──► Mergify auto-squash-merges to main, branch deleted
+          fail ──► fix the regression, push, and /merge again
+```
+
+---
+
+## CI Tiers
+
+### Tier 1: Pre-commit (every PR push)
+
+| Attribute | Value |
+|-----------|-------|
+| Triggered by | Every push to any PR branch, plus pushes to `main` |
+| Runs on | GitHub Actions, `ubuntu-latest` |
+| Duration | ~2 minutes |
+
+**Checks run** (from `.pre-commit-config.yaml`, stage: `manual`):
+
+| Hook | What it checks |
+|------|---------------|
+| `yapf` | Python code formatting |
+| `ruff` | Python linting and auto-fixable style issues |
+| `codespell` | Spelling errors in code and docs |
+| `pymarkdown` | Markdown formatting |
+| `actionlint` | GitHub Actions workflow syntax |
+| `mypy` | Static type checking (Python 3.10 target) |
+| `check-filenames` | No spaces in tracked filenames |
+
+A failure here means code style or type issues. Run `pre-commit run --all-files` locally to
+replicate CI results before pushing.
+
+---
+
+### Tier 2: Fastcheck (path-filtered, every PR push)
+
+| Attribute | Value |
+|-----------|-------|
+| Triggered by | Every push; the monorepo-diff plugin skips tests for unchanged paths |
+| Runs on | Buildkite, Modal GPU instances |
+| Duration | ~10-20 minutes per test (run in parallel) |
+
+**Tests and their path triggers:**
+
+| Buildkite label | `TEST_TYPE` | Triggers when you change |
+|-----------------|-------------|--------------------------|
+| Encoder Tests | `encoder` | `fastvideo/models/encoders/**`, `fastvideo/models/loader/**`, `fastvideo/tests/encoders/**`, `pyproject.toml`, `docker/Dockerfile.python3.12` |
+| VAE Tests | `vae` | `fastvideo/models/vaes/**`, `fastvideo/models/loader/**`, `fastvideo/tests/vaes/**`, `pyproject.toml`, `docker/Dockerfile.python3.12` |
+| Transformer Tests | `transformer` | `fastvideo/models/dits/**`, `fastvideo/models/loader/**`, `fastvideo/tests/transformers/**`, `fastvideo/layers/**`, `fastvideo/attention/**`, `pyproject.toml`, `docker/Dockerfile.python3.12` |
+| Kernel Tests | `kernel_tests` | `fastvideo-kernel/**`, `pyproject.toml`, `docker/Dockerfile.python3.12` |
+| Unit Tests | `unit_test` | `fastvideo/**`, `.buildkite/**`, `.github/**`, `pyproject.toml`, `docker/Dockerfile.python3.12` |
+
+A Fastcheck failure means a component-level regression. Check the Buildkite build log for the
+failing test's output.
+
+---
+
+### Tier 3: Full Test Suite (triggered by `ready` label)
+
+| Attribute | Value |
+|-----------|-------|
+| Triggered by | Adding the `ready` label to the PR (via `/merge` command), or a `/test full` command |
+| Runs on | Buildkite, Modal GPU instances |
+| Duration | 60-90 minutes total (tests run in parallel, path-filtered) |
+
+**Tests:**
+
+| Buildkite label | `TEST_TYPE` | Timeout |
+|-----------------|-------------|---------|
+| SSIM Tests | `ssim` | 90 min |
+| LoRA Inference Tests | `inference_lora` | 20 min |
+| Training Tests | `training` | 15 min |
+| Distillation DMD Tests | `distillation_dmd` | 15 min |
+| Self-Forcing Tests | `self_forcing` | 15 min |
+| LoRA Training Tests | `training_lora` | 15 min |
+| Training Tests VSA | `training_vsa` | 15 min |
+| Inference Tests VMoBA | `inference_vmoba` | 15 min |
+| Performance Tests | `performance` | 30 min |
+| API Server Tests | `api_server` | 30 min |
+
+If a Full Suite test fails, check the Buildkite build log for the failing step's output.
+Fix the regression, push, and comment `/merge` again to re-trigger.
+
+---
+
+## Auto-merge Flow
+
+Mergify prevents untested code from landing on `main` by gating squash-merge on the Full
+Suite passing directly on the PR branch.
+
+**How it works:**
+
+1. A developer comments `/merge` on an approved PR (or a maintainer adds the `ready` label).
+2. The `ready` label triggers `ci-trigger-full-suite.yml`, which calls the Buildkite API to
+   run the Full Suite on the PR branch itself.
+3. While the Full Suite runs, Mergify also auto-rebases the PR branch against `main` if it
+   is behind and has no conflicts.
+4. Once the Full Suite posts `full-suite-passed`, Mergify checks all **merge conditions**:
+   - `pre-commit` check is green
+   - `fastcheck-passed` check is green
+   - `full-suite-passed` check is green
+   - At least 1 approved review (`#approved-reviews-by>=1`)
+   - PR title starts with a valid `[type]` tag
+   - PR is not a draft
+   - No merge conflicts
+5. If all conditions pass, Mergify squash-merges to `main` automatically. The branch is
+   deleted after merge.
+6. If the Full Suite fails, the developer fixes the issue, pushes, and comments `/merge`
+   again to re-trigger.
+
+**Merge conditions summary:**
+
+| Condition | Meaning |
+|-----------|---------|
+| `check-success~=pre-commit` | Tier 1 pre-commit must be green |
+| `check-success=fastcheck-passed` | Tier 2 Fastcheck must be green |
+| `check-success=full-suite-passed` | Tier 3 Full Suite must be green |
+| `#approved-reviews-by>=1` | At least one approved review |
+| `title~=(?i)^\[(feat|bugfix|...)` | PR title has a valid type tag |
+| `-draft` | PR is not in draft state |
+| `-conflict` | No merge conflicts with base branch |
+| `-closed` | PR is still open |
+
+---
+
+## Label System
+
+Labels are applied automatically. You don't need to set them manually.
+
+### Type Labels (from PR title prefix)
+
+Applied by Mergify based on the `[tag]` at the start of the PR title.
+
+| Label | Matched title prefix | Meaning |
+|-------|---------------------|---------|
+| `type: feat` | `[feat]` or `[feature]` | New feature or capability |
+| `type: bugfix` | `[bugfix]` or `[fix]` | Bug fix |
+| `type: refactor` | `[refactor]` | Code restructuring, no behavior change |
+| `type: perf` | `[perf]` | Performance improvement |
+| `type: ci` | `[ci]` | CI/CD or tooling changes |
+| `type: docs` | `[doc]` or `[docs]` | Documentation only |
+| `type: misc` | `[misc]` or `[chore]` | Housekeeping, dependency bumps |
+| `type: new-model` | `[new-model]` | Adding a new model |
+
+### Scope Labels (from changed files)
+
+Applied by Mergify based on which paths you modified. Multiple scope labels can be added.
+
+| Label | File paths that trigger it |
+|-------|---------------------------|
+| `scope: training` | `fastvideo/train/`, `fastvideo/training/`, `fastvideo/distillation/`, `examples/train/`, `examples/training/`, `examples/distill/` |
+| `scope: inference` | `fastvideo/pipelines/basic/`, `fastvideo/pipelines/stages/`, `fastvideo/pipelines/samplers/`, `fastvideo/entrypoints/`, `fastvideo/worker/`, `fastvideo/api/sampling_param.py`, `fastvideo/configs/pipelines/`, `examples/inference/` |
+| `scope: attention` | `fastvideo/attention/` |
+| `scope: kernel` | `fastvideo-kernel/`, `csrc/` |
+| `scope: data` | `fastvideo/dataset/`, `fastvideo/pipelines/preprocess/`, `examples/preprocessing/` |
+| `scope: infra` | `.github/`, `.buildkite/`, `fastvideo/tests/`, `docker/` |
+| `scope: distributed` | `fastvideo/distributed/` |
+| `scope: docs` | `docs/` |
+| `scope: ui` | `ui/` |
+| `scope: model` | `fastvideo/models/`, `fastvideo/layers/`, `fastvideo/configs/models/` |
+
+### Process Labels
+
+| Label | Who sets it | Meaning |
+|-------|-------------|---------|
+| `ready` | Developer (`/merge` command) or maintainer | Triggers Full Suite and enables auto-merge |
+| `needs-rebase` | Mergify (automatic) | PR has merge conflicts; rebase needed |
+| `do-not-merge` | Maintainer | Blocks queue entry regardless of other conditions |
+
+---
+
+## PR Title Format
+
+All PR titles targeting `main` must start with a bracketed type tag. This is enforced by a
+Mergify merge protection rule and is required before a PR can be squash-merged.
+
+**Format:**
+
+```
+[type] Short description
+```
+
+**Valid type tags:**
+
+`feat`, `feature`, `bugfix`, `fix`, `refactor`, `perf`, `ci`, `doc`, `docs`, `misc`, `chore`,
+`kernel`, `new-model`
+
+**Valid examples:**
+
+```
+[feat] Add causal Wan pipeline
+[bugfix] Fix VAE temporal tiling corruption
+[refactor] Restructure training framework
+[perf] Optimize FlashAttention kernel dispatch
+[docs] Add inference guide for LoRA
+[new-model] Port HunyuanVideo 1.5 to FastVideo
+```
+
+**Invalid examples (will block merge):**
+
+```
+Add causal Wan pipeline          ← missing type tag
+FEAT: Add pipeline               ← wrong format
+feat: Add pipeline               ← square brackets required
+```
+
+If your title is invalid, Mergify posts a comment explaining the required format and the
+merge protection check will remain failed until you update the title.
+
+---
+
+## Slash Commands
+
+Slash commands let contributors and maintainers trigger CI actions directly from PR comments.
+**Write permission to the repository is required.**
+
+The command is recognized within a few seconds. The workflow reacts with a 🚀 emoji to confirm.
+
+### `/merge`
+
+```
+/merge
+```
+
+Adds the `ready` label to the PR, which triggers the Full Suite on your PR branch and
+enables Mergify to auto-squash-merge once all conditions pass.
+
+The command first removes the `ready` label if it is already present, then re-adds it. This
+ensures the `labeled` event fires and a fresh Full Suite build is started even on a re-try.
+
+### `/test <name>`
+
+```
+/test <name>
+```
+
+Triggers a specific Buildkite test or suite on the current PR branch.
+
+| Command | Runs | Maps to `TEST_TYPE` |
+|---------|------|---------------------|
+| `/test encoder` | Encoder Tests (Fastcheck) | `encoder` |
+| `/test vae` | VAE Tests (Fastcheck) | `vae` |
+| `/test transformer` | Transformer Tests (Fastcheck) | `transformer` |
+| `/test kernel` | Kernel Tests (Fastcheck) | `kernel_tests` |
+| `/test unit` | Unit Tests (Fastcheck) | `unit_test` |
+| `/test ssim` | SSIM regression tests | `ssim` |
+| `/test training` | Training pipeline tests | `training` |
+| `/test lora-inference` | LoRA inference tests | `inference_lora` |
+| `/test lora-training` | LoRA training tests | `training_lora` |
+| `/test distillation` | DMD distillation tests | `distillation_dmd` |
+| `/test self-forcing` | Self-Forcing tests | `self_forcing` |
+| `/test vsa` | VSA training tests | `training_vsa` |
+| `/test vmoba` | VMoBA inference tests | `inference_vmoba` |
+| `/test performance` | Performance benchmarks | `performance` |
+| `/test api` | API server integration tests | `api_server` |
+| `/test full` | Entire Full Suite | all (with `TEST_SCOPE=full`) |
+| `/test fastcheck` | Entire Fastcheck suite | fastcheck (with `TEST_SCOPE=fastcheck`) |
+| `/test pre-commit` | Pre-commit checks on PR code | — (runs `ci-precommit.yml` via `workflow_call`) |
+
+**Re-running failed tests:** When you use `/test <name>` to re-run a specific failed test,
+the resulting Buildkite check uses the same name as the original (e.g., `/test encoder`
+creates `buildkite/ci/microscope-encoder-tests`). This overwrites the failed check status.
+Once all tests in a tier pass, the aggregate status (`fastcheck-passed` or
+`full-suite-passed`) is automatically updated to `success` by the `ci-aggregate-status.yml`
+workflow.
+
+**How aggregate status refresh works:**
+
+1. `/test <name>` triggers a Buildkite build with `TEST_SCOPE=direct`. The test step uses
+   the same label as its fastcheck/full-suite counterpart, so the resulting GitHub check
+   overwrites the original.
+2. When the build completes, Buildkite's `notify` posts a `direct-test-completed` commit
+   status. This is the only signal that triggers the aggregate workflow — intermediate step
+   status updates do not trigger it.
+3. `ci-aggregate-status.yml` fires, calls `getCombinedStatusForRef` to fetch the latest
+   status for every context on that commit (each context returns only its most recent
+   state), groups them by prefix (`microscope-*` → fastcheck, `test-tube-*`/`bar-chart-*`
+   → full suite), and posts `fastcheck-passed: success` or `full-suite-passed: success` if
+   all entries in the group are `success`.
+4. Tests that were never triggered (skipped by monorepo-diff) have no status entry and do
+   not block the aggregate.
+
+---
+
+## Auto Branch Cleanup
+
+After a PR is squash-merged to `main`, Mergify automatically deletes the head branch.
+Protected branches (`main`, `master`, `release/*`) are never deleted.
+
+---
+
+## Workflow File Reference
+
+| Filename | Trigger | What it does |
+|----------|---------|-------------|
+| `ci-precommit.yml` | Every push / PR against `main` | Runs pre-commit hooks (yapf, ruff, mypy, codespell, pymarkdown, actionlint, check-filenames) |
+| `ci-trigger-full-suite.yml` | `ready` label added to a PR | Calls Buildkite API to run Full Suite on the PR branch |
+| `ci-slash-commands.yml` | PR comment starting with `/merge` or `/test` | Handles slash commands; adds `ready` label or triggers Buildkite |
+| `ci-aggregate-status.yml` | Any Buildkite commit status update | Checks if all tests in a tier passed; updates `fastcheck-passed` or `full-suite-passed` |
+| `community-issue-labeler.yml` | Issue opened or edited | Auto-labels issues by keyword matching against title and body |
+| `community-welcome.yml` | First contribution | Posts a welcome comment for first-time contributors |
+| `community-stale.yml` | Scheduled | Marks and closes stale issues and PRs |
+| `infra-build-image.yml` | Manual (`workflow_dispatch`) | Builds Docker images for CI |
+| `infra-docs.yml` | Changes to `docs/` merged to `main` | Builds and deploys documentation to GitHub Pages |
+| `publish-fastvideo.yml` | Version bump | Publishes `fastvideo` package to PyPI |
+| `publish-kernel.yml` | Version bump | Publishes `fastvideo-kernel` package to PyPI |
+| `publish-comfyui.yml` | Version bump | Publishes ComfyUI node package to PyPI |

docs/contributing/coding_agents.md

@@ -44,7 +44,7 @@ FastVideo maps a Diffusers-style repo into a pipeline like:
 - `fastvideo/configs/models/*`: arch configs and `param_names_mapping` for
   weight name translation.
 - `fastvideo/configs/pipelines/*`: pipeline wiring (component classes + names).
-- `fastvideo/configs/sample/*`: default runtime sampling parameters.
+- `fastvideo/api/sampling_param.py`: runtime sampling parameters.
 - `fastvideo/pipelines/basic/*`: end-to-end pipeline logic built from stages.
 - `model_index.json`: the HF repo entrypoint that maps component names to
   classes and weight files.
@@ -55,7 +55,7 @@ Minimal usage example (based on `examples/inference/basic/basic.py`):
 
 ```python
 from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
+from fastvideo.api.sampling_param import SamplingParam
 
 model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"  # or official_weights/<model_name>/
 generator = VideoGenerator.from_pretrained(model_id, num_gpus=1)
@@ -296,8 +296,10 @@ Action:
 
 - Add or reuse a numerical parity test that loads the official model and the
   FastVideo model and compares outputs.
-- See examples in `tests/local_tests/` (e.g., `tests/local_tests/upsamplers/`)
-  and the commands in `tests/local_tests/README.md`.
+- See examples in `tests/local_tests/` organized by model family
+  (e.g., `tests/local_tests/sd35/`, `tests/local_tests/ltx2/`,
+  `tests/local_tests/stable_audio/`) and the navigation index in
+  `tests/local_tests/README.md`.
 - If there are discrepancies, add opt‑in logging to both models and compare
   activation summaries (layer output sums, per‑stage logs).
 - First align the loaded weights (validate `param_names_mapping`).
@@ -319,7 +321,8 @@ Purpose:
 
 - `fastvideo/configs/pipelines/` describes pipeline wiring and model module
   names.
-- `fastvideo/configs/sample/` defines default runtime parameters.
+- `fastvideo/api/sampling_param.py` defines runtime sampling parameters.
+  Defaults come from profiles in `fastvideo/pipelines/basic/<family>/profiles.py`.
 
 Action:
 
@@ -347,7 +350,8 @@ Purpose:
 
 Action:
 
-- Add a pipeline parity test under `tests/local_tests/pipelines/`.
+- Add a pipeline parity test under `tests/local_tests/<family>/`
+  (e.g., `tests/local_tests/<family>/test_<family>_pipeline_parity.py`).
 - See the [Testing Guide](testing.md) for test conventions.
 
 ### 7) Add user‑facing examples
@@ -474,7 +478,7 @@ FastVideo integration.
 3. Pipeline wiring.
    - Pipeline: `fastvideo/pipelines/basic/wan/wan_pipeline.py`
    - Pipeline config: `fastvideo/configs/pipelines/wan.py`
-   - Sampling defaults: `fastvideo/configs/sample/wan.py`
+   - Sampling defaults: `fastvideo/pipelines/basic/wan/profiles.py`
 
 4. Minimal example.
    - Script: `examples/inference/basic/basic.py`

docs/contributing/developer_env/runpod.md

@@ -1,65 +1,195 @@
+# RunPod Development Environment
 
-# 📦 Developing FastVideo on RunPod
+RunPod gives you on-demand cloud GPUs for FastVideo development. It's useful when you need a beefy GPU to test training runs, benchmark inference, or reproduce results without waiting for shared cluster time.
 
-You can easily use the FastVideo Pod Template on [RunPod](https://www.runpod.io) for development or experimentation.
+## Prerequisites
 
-## Creating a new pod
+- A [RunPod](https://www.runpod.io) account with billing configured
+- An SSH key pair. If you don't have one, generate it with `ssh-keygen -t ed25519`
+- Your public key (`~/.ssh/id_ed25519.pub`) ready to paste into RunPod
+
+## Step 1: Create a Pod
+
+**1. Verify your account**
+
+Make sure you're logged into the right RunPod account before spending credits.
 
-- Make sure you are using the correct RunPod account.
 ![RunPod Account Selection](../../assets/images/runpod_account.png)
 
-- Use "Additional Filters" to select CUDA 12.8.
+**2. Filter by CUDA version**
+
+Use "Additional Filters" to select CUDA 12.8.
+
 ![RunPod CUDA selection](../../assets/images/runpod_cuda.png)
 
-- Click "Deploy" and Pick a single A40 or RTX 4090 GPU.
+**3. Select a GPU**
+
+Click "Deploy" and pick a GPU. See [GPU Recommendations](#gpu-recommendations) below for guidance on which GPU to choose.
+
 ![RunPod GPU Selection](../../assets/images/runpod_deploy.png)
 
-- Select the "FastVideo" or "fastvideo-dev" Pod Template.
+**4. Pick the FastVideo template**
+
+Select the "FastVideo" or "fastvideo-dev" Pod Template. This pulls the pre-built image that includes all dependencies, Flash Attention, and a ready-to-use `uv` environment.
+
 ![RunPod Pod Template Selection](../../assets/images/runpod_create.png)
 
-- Set the Pod name to "`<name>-<FastVideo>-<date>`".
+**5. Name your pod**
+
+Use a memorable name like `yourname-fastvideo-2026-03-28`. This helps if you have multiple pods running.
+
+**6. Add a persistent volume (recommended)**
+
+Attach a network volume to `/root/.cache` or `/models` for storing downloaded model weights. Models can be 10-50 GB each, and re-downloading them every session wastes time and bandwidth.
+
+**7. Deploy**
+
+Click Deploy. The pod takes a few minutes to start while the image pulls. You'll see it transition to "Running" in your dashboard.
+
+## Step 2: Connect via SSH
+
+Once the pod is running, find the "SSH over exposed TCP" connection string in the pod dashboard.
 
-- Finally, once the pod is deployed (will take a few minutes as the image is being pulled), you can SSH into it using "SSH exposed over TCP". You'll need to use the matching private ssh key you provided.
 ![RunPod SSH](../../assets/images/runpod_ssh.png)
 
-## Working with the pod
-
-After SSH'ing into your pod, you'll find the correct `uv` environment already activated and you should be in /FastVideo/ directory. Make sure to use /FastVideo/ for all your work.
-
-To pull in the latest changes from the GitHub repo:
+Connect with:
 
 ```bash
-cd /FastVideo
-git pull
+ssh root@<pod-ip> -p <port> -i ~/.ssh/id_ed25519
 ```
 
-Run your development workflows as usual:
+RunPod also supports VS Code Remote SSH if you prefer an IDE.
 
-```bash
-# Run linters
-pre-commit run --all-files
+### Custom template (advanced)
 
-# Run tests
-pytest tests/
-```
-
-Make sure to push your changes back to the GitHub repo as nothing will be saved to the pod when it is terminated.
-
-After you are done with your work, you can terminate the pod by clicking the "Terminate" and "Delete" buttons. Remember if the pod is not completely deleted, Runpod will keep charging you for it.
-
-## Extra Information:
-If you need to customize the pod template this section has some useful information. For the most part you can leave the defaults of the FastVideo Pod Template.
-
-When creating your pod template, use this image:
+If you're setting up a pod from scratch instead of the FastVideo template, use this image:
 
 ```
 ghcr.io/hao-ai-lab/fastvideo/fastvideo-dev:py3.12-latest
 ```
 
-Paste Container Start Command to support SSH ([RunPod Docs](https://docs.runpod.io/pods/configuration/use-ssh)):
+And paste this as the Container Start Command to enable SSH ([RunPod docs](https://docs.runpod.io/pods/configuration/use-ssh)):
 
 ```bash
 bash -c "apt update;DEBIAN_FRONTEND=noninteractive apt-get install openssh-server -y;mkdir -p ~/.ssh;cd $_;chmod 700 ~/.ssh;echo \"$PUBLIC_KEY\" >> authorized_keys;chmod 700 authorized_keys;service ssh start;sleep infinity"
 ```
 
 ![RunPod template configuration](../../assets/images/runpod_template.png)
+
+## Step 3: Set Up FastVideo
+
+After SSH'ing in, the `uv` virtual environment at `/opt/venv` is already activated (configured in `.bashrc` and `.profile`). You land in the `/FastVideo` directory.
+
+**Clone or pull the repo**
+
+If the pod already has the FastVideo repo:
+
+```bash
+cd /FastVideo
+git pull
+```
+
+If starting from a blank pod:
+
+```bash
+git clone https://github.com/hao-ai-lab/FastVideo.git /FastVideo
+cd /FastVideo
+```
+
+**Install the package**
+
+```bash
+uv pip install -e ".[dev]"
+```
+
+The Docker image already includes Flash Attention and most heavy dependencies, so this is fast.
+
+**Build the custom kernels (optional)**
+
+VSA and STA attention kernels aren't in the Docker image by default. Build them if you're working on attention backends or need maximum inference performance:
+
+```bash
+cd /FastVideo/fastvideo-kernel
+./build.sh
+```
+
+The build script detects your GPU architecture automatically. An A100 or H100 takes about 5-10 minutes.
+
+**Verify the setup**
+
+```bash
+cd /FastVideo
+python -c "import fastvideo; print('OK')"
+pytest tests/ -q --no-header
+```
+
+## Development Workflow
+
+### Editing code on RunPod
+
+Two common approaches:
+
+**Option A: Edit on RunPod directly**
+
+Use VS Code Remote SSH or `vim`/`nano` on the pod. Commit and push when you're ready:
+
+```bash
+cd /FastVideo
+git add .
+git commit -m "your change"
+git push
+```
+
+**Option B: Edit locally, sync to RunPod**
+
+Work in your local repo, then pull on the pod:
+
+```bash
+# On RunPod:
+cd /FastVideo
+git pull
+```
+
+This keeps your local tools (editor, linters) intact while running GPU workloads on the pod.
+
+### Running linters and tests
+
+```bash
+# Lint
+pre-commit run --all-files
+
+# Full test suite
+pytest tests/
+
+# Just package tests
+pytest fastvideo/tests/ -v
+```
+
+### Storing models
+
+If you attached a persistent volume, point your model downloads there:
+
+```bash
+export HF_HOME=/models/huggingface
+export TRANSFORMERS_CACHE=/models/huggingface
+```
+
+Add these to `/root/.bashrc` so they persist across SSH sessions. The volume survives pod termination, so you only download models once.
+
+### Terminating the pod
+
+When you're done, push any commits you want to keep. RunPod does not save pod storage after termination.
+
+Go to your RunPod dashboard, click "Terminate", then "Delete". A pod that's stopped but not deleted still charges you for storage. Fully delete it to stop all charges.
+
+## GPU Recommendations
+
+| GPU | VRAM | Good for |
+|-----|------|----------|
+| RTX 4090 | 24 GB | Inference testing, small model fine-tuning, quick iteration |
+| A40 | 48 GB | Mid-size training runs, 480p video generation |
+| A100 (40 GB) | 40 GB | Multi-GPU inference, training with sequence parallelism |
+| A100 (80 GB) | 80 GB | Large model training, 720p+ video generation |
+| H100 | 80 GB | Heavy training, benchmarking, kernel development |
+
+For most development work, a single RTX 4090 or A40 is sufficient and cost-effective. Use A100/H100 when you need to reproduce training results at scale or test multi-GPU features.

docs/contributing/overview.md

@@ -49,7 +49,7 @@ git clone https://github.com/hao-ai-lab/FastVideo.git && cd FastVideo
 Install FastVideo in editable mode and set up hooks:
 
 ```bash
-uv pip install -e .[dev]
+uv pip install -e ".[dev]"
 
 # Optional: FlashAttention (builds native kernels)
 uv pip install flash-attn --no-build-isolation -v

docs/contributing/pull_requests.md

@@ -0,0 +1,223 @@
+# Contributing via Pull Requests
+
+This guide walks through the PR workflow: title format, labels, CI pipeline, and getting
+your changes merged.
+
+---
+
+## PR Title Format (Required)
+
+Every PR targeting `main` must start with a type tag in square brackets. This is checked by
+Mergify before any merge is allowed.
+
+**Format:**
+
+```
+[type] Short description of the change
+```
+
+**Valid type tags:**
+
+| Tag | When to use |
+|-----|-------------|
+| `[feat]` or `[feature]` | New feature or capability |
+| `[bugfix]` or `[fix]` | Bug fix |
+| `[refactor]` | Code restructuring with no behavior change |
+| `[perf]` | Performance improvement |
+| `[ci]` | CI/CD or build tooling changes |
+| `[doc]` or `[docs]` | Documentation only |
+| `[misc]` or `[chore]` | Housekeeping, dependency bumps, minor cleanup |
+| `[kernel]` | CUDA kernel changes in `fastvideo-kernel/` |
+| `[new-model]` | Adding a new model or pipeline |
+
+**Examples:**
+
+```
+[feat] Add causal Wan 2.2 I2V pipeline
+[bugfix] Fix VAE temporal tiling corruption on H100
+[refactor] Restructure distributed attention dispatch
+[docs] Add LoRA finetuning guide
+[new-model] Port HunyuanVideo 1.5 to FastVideo
+```
+
+If your title is missing the tag, Mergify will post a comment listing the valid formats.
+Update the title and the check will re-evaluate automatically.
+
+---
+
+## Labels
+
+Labels are applied automatically based on your PR title and the files you changed. You don't
+need to set them manually.
+
+**Type label** — set from the `[tag]` in your title:
+`type: feat`, `type: bugfix`, `type: refactor`, `type: perf`, `type: ci`, `type: docs`,
+`type: misc`, `type: new-model`
+
+**Scope labels** — set from which files you modified (multiple labels can apply):
+`scope: training`, `scope: inference`, `scope: attention`, `scope: kernel`, `scope: data`,
+`scope: infra`, `scope: distributed`, `scope: docs`, `scope: ui`, `scope: model`
+
+**Process labels** — set during review and merge:
+
+| Label | Who sets it | Meaning |
+|-------|-------------|---------|
+| `ready` | You (`/merge` comment) or a maintainer | Triggers Full Suite and enables auto-merge |
+| `needs-rebase` | Mergify (automatic) | Your PR has conflicts; rebase against `main` |
+| `do-not-merge` | Maintainer | Blocks merge regardless of CI status |
+
+---
+
+## CI Pipeline
+
+Three tiers run automatically on every PR.
+
+**Tier 1: Pre-commit (~2 min) — runs on every push**
+
+GitHub Actions checks formatting, linting, type correctness, and spelling using pre-commit
+hooks: yapf, ruff, mypy, codespell, pymarkdown, actionlint, and check-filenames.
+
+**Tier 2: Fastcheck (~10-20 min) — runs on every push, path-filtered**
+
+Buildkite runs GPU tests only for the components you changed. If you only modified
+`fastvideo/models/vaes/`, only VAE Tests run. Tests run in parallel.
+
+**Tier 3: Full Suite (~60-90 min) — triggered by the `ready` label**
+
+When you comment `/merge` (or a maintainer adds the `ready` label), Buildkite runs the
+complete test suite on your PR branch: SSIM regression, LoRA inference and training,
+distillation, self-forcing, VSA, VMoBA, performance benchmarks, and API server tests.
+
+---
+
+## Getting Your PR Merged
+
+**Step-by-step:**
+
+1. Open a PR with a title that starts with a valid `[type]` tag.
+2. Push your changes. Pre-commit and Fastcheck run automatically.
+3. Fix any pre-commit failures locally (`pre-commit run --all-files`) and push again.
+4. Wait for at least one approving review.
+5. Once approved and pre-commit is green, comment `/merge` on the PR.
+6. The `ready` label is added, which triggers the Full Suite on your PR branch.
+7. Mergify also auto-rebases your branch against `main` if it is behind and conflict-free.
+8. If all Full Suite tests pass and all merge conditions are met (approval, valid title,
+   pre-commit green, fastcheck green, no draft, no conflicts), Mergify squash-merges to
+   `main` automatically. Your branch is deleted.
+9. If a Full Suite test fails, check the Buildkite build log for the failing step. Fix the
+   issue, push, and comment `/merge` again. You can also re-run individual failed tests
+   with `/test <name>` — see below.
+
+!!! note
+    Only contributors with write permission to the repository can trigger slash commands.
+    If you're an external contributor, ask a maintainer to run `/merge` or add the `ready`
+    label for you.
+
+---
+
+## Running Tests On Demand
+
+Comment on your PR to trigger specific tests independently of the auto-merge flow.
+
+**Trigger the entire Full Suite:**
+
+```
+/test full
+```
+
+**Trigger the Fastcheck suite:**
+
+```
+/test fastcheck
+```
+
+**Trigger individual tests:**
+
+```
+/test encoder          # Encoder component tests
+/test vae              # VAE component tests
+/test transformer      # Transformer / DiT tests
+/test kernel           # CUDA kernel tests
+/test unit             # Unit tests
+
+/test ssim             # SSIM regression tests
+/test training         # Training pipeline tests
+/test lora-inference   # LoRA inference tests
+/test lora-training    # LoRA training tests
+/test distillation     # DMD distillation tests
+/test self-forcing     # Self-Forcing distillation tests
+/test vsa              # VSA training tests
+/test vmoba            # VMoBA inference tests
+/test performance      # Performance benchmarks
+/test api              # API server integration tests
+/test pre-commit       # Pre-commit checks on PR code
+```
+
+The workflow reacts with a 🚀 emoji to confirm the command was received.
+
+When you re-run an individual test with `/test <name>`, the new result overwrites the
+original failed check (same Buildkite check name). Once all tests in a tier pass, the
+`fastcheck-passed` or `full-suite-passed` status is automatically updated.
+
+---
+
+## Troubleshooting
+
+### Pre-commit fails
+
+Run locally to reproduce and auto-fix:
+
+```bash
+# Install pre-commit if needed
+uv pip install pre-commit
+pre-commit install
+
+# Run all checks on all files
+pre-commit run --all-files
+```
+
+Common quick fixes:
+
+- **yapf**: `yapf -i <file>` (Python formatting)
+- **ruff**: `ruff check --fix <file>` (linting)
+- **codespell**: `codespell --write-changes <file>` (spelling)
+
+### PR title format check fails
+
+Update your title to start with a valid type tag. The Mergify merge protection check
+re-evaluates automatically after you save the title.
+
+Valid tags: `feat`, `feature`, `bugfix`, `fix`, `refactor`, `perf`, `ci`, `doc`, `docs`,
+`misc`, `chore`, `kernel`, `new-model`
+
+### My PR has merge conflicts (`needs-rebase` label)
+
+Rebase against `main` and force-push:
+
+```bash
+git fetch origin main
+git rebase origin/main
+# Resolve any conflicts, then:
+git push --force-with-lease
+```
+
+Mergify removes the `needs-rebase` label automatically once conflicts are resolved.
+
+### Full Suite failed after `/merge`
+
+The Full Suite found a regression. Check the failing Buildkite step's output for assertion
+errors or tracebacks.
+
+Common causes:
+
+- Test failures caused by your code changes
+- Missing dependency in `pyproject.toml`
+- GPU memory issue (some tests require specific hardware like L40S or H100)
+- Kernel build failure (if you changed `fastvideo-kernel/`)
+
+After fixing, push and comment `/merge` again.
+
+### I'm an external contributor without write permission
+
+You can't use slash commands directly. After your PR is approved, ask a maintainer to
+comment `/merge` or add the `ready` label.

docs/contributing/testing.md

@@ -23,13 +23,18 @@ SSIM tests are located in `fastvideo/tests/ssim`. These tests generate videos us
 
 ```
 fastvideo/tests/ssim/
-├── <GPU>_reference_videos/   # Reference videos organized by GPU type (e.g., L40S_reference_videos)
-│   ├── <Model_Name>/
-│   │   ├── <Backend>/        # e.g., FLASH_ATTN, TORCH_SDPA
-│   │   │   └── <Video_File>
+├── reference_videos/
+│   ├── default/
+│   │   └── <GPU>_reference_videos/
+│   │       ├── <Model_Name>/
+│   │       │   ├── <Backend>/        # e.g., FLASH_ATTN, TORCH_SDPA
+│   │       │   │   └── <Video_File>
+│   └── full_quality/
+│       └── <GPU>_reference_videos/
 ├── test_causal_similarity.py
-├── test_inference_similarity.py
-├── update_reference_videos.sh
+├── test_wan_t2v_similarity.py
+├── test_wan_i2v_similarity.py
+├── reference_videos_cli.py
 └── ...
 ```
 
@@ -37,7 +42,7 @@ fastvideo/tests/ssim/
 
 To add a new SSIM test, follow these steps:
 
-1. **Create or Update a Test File**: You can add a new test function to an existing file (like `test_inference_similarity.py`) or create a new one if testing a distinct category of models.
+1. **Create or Update a Test File**: Prefer model-specific files (for example `test_wan_t2v_similarity.py`) and create a new one when testing a distinct model or pipeline.
 
 2. **Define Model Parameters**: Define the configuration for the model you want to test. This includes model path, dimensions, inference steps, and other generation parameters. **Note:** Consider using lower `num_inference_steps` or reduced resolution (e.g., 480p instead of 720p) to keep test execution time reasonable, provided it doesn't compromise the test's ability to detect regression.
 
@@ -81,10 +86,15 @@ To add a new SSIM test, follow these steps:
    ```
 
 4. **Reference Videos**:
-   * When running the test for the first time (or when updating the reference), the test will fail because the reference video is missing. The generated video will be saved in `fastvideo/tests/ssim/generated_videos`.
+   * When running the test for the first time (or when updating the reference), the test will fail because the reference video is missing. The generated video will be saved in `fastvideo/tests/ssim/generated_videos/<quality-tier>/<GPU>_reference_videos`.
    * Inspect the generated video to ensure it meets quality expectations.
-   * Move the generated video to the appropriate reference folder: `fastvideo/tests/ssim/<GPU>_reference_videos/<Model>/<Backend>/`.
-   * You can use the helper script `update_reference_videos.sh` to automate copying videos from `generated_videos` to `L40S_reference_videos`. Note: Check the script to ensure paths match your environment (it defaults to `L40S_reference_videos`).
+   * Move the generated video to the appropriate quality/GPU reference folder:
+     `fastvideo/tests/ssim/reference_videos/<quality-tier>/<GPU>_reference_videos/<Model>/<Backend>/`.
+   * You can use the helper CLI to copy generated videos into a reference folder:
+     `python fastvideo/tests/ssim/reference_videos_cli.py copy-local --quality-tier default --reference-dir fastvideo/tests/ssim/reference_videos/default/L40S_reference_videos`
+   * Upload/download can target both quality tiers and specific GPU folders:
+     `python fastvideo/tests/ssim/reference_videos_cli.py upload --quality-tier all`
+     `python fastvideo/tests/ssim/reference_videos_cli.py download --quality-tier full_quality --device-folder H200_reference_videos`
 
 ### Running Tests Locally
 
@@ -96,36 +106,113 @@ pytest fastvideo/tests/ssim/ -vs
 
 Ensure you have the necessary GPUs available as defined in your test parameters.
 
-## Modal Workflow
+## CI Integration
 
-FastVideo uses [Modal](https://modal.com/) for running tests in a CI environment. The workflow scripts are located in `fastvideo/tests/modal/`.
+FastVideo uses [Modal](https://modal.com/) for running tests in a CI environment. The
+workflow scripts are located in `fastvideo/tests/modal/`.
+
+### Buildkite Pipeline
+
+Tests are orchestrated by Buildkite (`.buildkite/pipeline.yml`) and executed on Modal GPU
+instances. The pipeline runs in two modes:
+
+**Fastcheck** — runs on every PR push, path-filtered. Only tests for the components you
+changed are triggered. Tests run in parallel.
+
+**Full Suite** — runs when a PR enters the Merge Queue (or when triggered manually via
+`/test full`). Covers SSIM regression, training, distillation, inference, and performance.
 
 ### `pr_test.py`
 
-The main entry point for CI tests is `fastvideo/tests/modal/pr_test.py`. This script defines Modal functions that execute the pytest suites on specific hardware (e.g., L40S, H100).
+The main entry point for CI tests is `fastvideo/tests/modal/pr_test.py`. This script defines
+Modal functions that execute the pytest suites on specific hardware (e.g., L40S, H100).
 
 ### Updating Modal Configuration
 
 If you add a new test that requires:
+
 * **Different GPU Hardware**: You may need to change the `@app.function(gpu=...)` decorator.
 * **Longer Execution Time**: Increase the `timeout` parameter.
-* **New Environment Variables/Secrets**: Add them to `secrets=[...]` or the image environment. For example, if your model is gated on Hugging Face, ensure `HF_API_KEY` is passed.
+* **New Environment Variables/Secrets**: Add them to `secrets=[...]` or the image
+  environment. For example, if your model is gated on Hugging Face, ensure `HF_API_KEY`
+  is passed.
 
-For SSIM tests, the `run_ssim_tests` function in `pr_test.py` currently runs:
+For SSIM tests, use `fastvideo/tests/modal/ssim_test.py`:
 
-```python
-@app.function(gpu="L40S:2", image=image, timeout=2700, secrets=[modal.Secret.from_dict({"HF_API_KEY": os.environ.get("HF_API_KEY", "")})])
-def run_ssim_tests():
-    run_test("hf auth login --token $HF_API_KEY && pytest ./fastvideo/tests/ssim -vs")
+```bash
+python -m modal run fastvideo/tests/modal/ssim_test.py::run_ssim_tests
 ```
 
-If your new test file is inside `fastvideo/tests/ssim`, it will automatically be picked up by this command. However, ensure that the `gpu="L40S:2"` configuration is sufficient for your model. If your model requires more GPUs (e.g., 4 or 8), you might need to create a separate Modal function or update the existing one.
+Target specific SSIM files/models:
+
+```bash
+python -m modal run fastvideo/tests/modal/ssim_test.py::run_ssim_tests \
+  --test-files test_wan_t2v_similarity.py \
+  --model-ids Wan2.1-T2V-1.3B-Diffusers
+```
+
+If HF token env vars are not set (`HF_API_KEY` / `HUGGINGFACE_HUB_TOKEN` /
+`HF_TOKEN`), the local entrypoint fails fast. To export raw `generated_videos`
+from Modal to the shared volume:
+
+```bash
+python -m modal run fastvideo/tests/modal/ssim_test.py::run_ssim_tests \
+  --sync-generated-to-volume
+```
+
+The raw export path is quality-tiered:
+
+* default params: `ssim_generated_videos/default/<subdir>/generated_videos`
+* full-quality params: `ssim_generated_videos/full_quality/<subdir>/generated_videos`
+
+The printed `modal volume get` command also downloads into a quality-specific
+local directory under `./generated_videos_modal/<quality-tier>`.
+
+To turn downloaded Modal outputs into local reference videos, use the matching
+quality tier with `copy-local`, for example:
+
+```bash
+python fastvideo/tests/ssim/reference_videos_cli.py copy-local \
+  --quality-tier full_quality \
+  --generated-dir ./generated_videos_modal/full_quality/L40S_reference_videos \
+  --device-folder L40S_reference_videos
+```
 
 ### Workflow Scripts
 
-The shell script that triggers these tests in the CI pipeline is located at `.buildkite/scripts/pr_test.sh`. If you add a new test category (e.g., a new folder outside of `ssim`), you will need to:
+The shell script that triggers tests in CI is `.buildkite/scripts/pr_test.sh`. If you add
+a new test category (e.g., a new folder outside of `ssim`), you will need to:
+
 1. Add a new function in `fastvideo/tests/modal/pr_test.py`.
 2. Add a new case in `.buildkite/scripts/pr_test.sh` to handle the new test type.
 
 !!! note
-    If you are a maintainer, you'll need to finally manually update the workflow script in Buildkite. Otherwise, a maintainer will help you update.
+    If you are a maintainer, update the workflow script in Buildkite after merging. Otherwise,
+    ask a maintainer for help.
+
+## Triggering Tests via Slash Commands
+
+Maintainers and contributors with write access can trigger individual test suites directly
+from a PR comment. The workflow reacts with a 🚀 emoji to confirm the command was received.
+
+```
+/test ssim              # SSIM regression tests
+/test training          # Training pipeline tests
+/test lora-training     # LoRA training tests
+/test lora-inference    # LoRA inference tests
+/test distillation      # DMD distillation tests
+/test self-forcing      # Self-Forcing tests
+/test vsa               # VSA training tests
+/test vmoba             # VMoBA inference tests
+/test performance       # Performance benchmarks
+/test api               # API server integration tests
+/test encoder           # Encoder component tests (Fastcheck)
+/test vae               # VAE component tests (Fastcheck)
+/test transformer       # Transformer / DiT tests (Fastcheck)
+/test kernel            # CUDA kernel tests (Fastcheck)
+/test unit              # Unit tests (Fastcheck)
+/test full              # Entire Full Suite
+/test fastcheck         # Entire Fastcheck suite
+```
+
+See [CI Architecture](ci_architecture.md) for the complete reference.

docs/design/inference_schema_parity_inventory.yaml

@@ -0,0 +1,480 @@
+status_definitions:
+  kept: "Public field remains on a public adapter surface with the same meaning."
+  moved: "Public field remains supported but normalizes into a different nested path."
+  preset_owned: "Public field remains supported only through a model/preset-specific surface."
+  compatibility_only: "Legacy public field remains adapter-only during migration and is not part of the canonical typed schema."
+  private_only: "Field should only be handled by private adapters and is not a public FastVideo compatibility promise."
+  internal_only: "Field is runtime/config plumbing and should not be part of the new public typed inference API."
+
+surfaces:
+  fastvideo_args:
+    moved:
+      model_path: generator.model_path
+      workload_type: generator.pipeline.workload_type
+      distributed_executor_backend: generator.engine.execution_backend
+      trust_remote_code: generator.trust_remote_code
+      revision: generator.revision
+      num_gpus: generator.engine.num_gpus
+      tp_size: generator.engine.parallelism.tp_size
+      sp_size: generator.engine.parallelism.sp_size
+      hsdp_replicate_dim: generator.engine.parallelism.hsdp_replicate_dim
+      hsdp_shard_dim: generator.engine.parallelism.hsdp_shard_dim
+      dist_timeout: generator.engine.parallelism.dist_timeout
+      lora_path: generator.pipeline.components.lora_path
+      dit_cpu_offload: generator.engine.offload.dit
+      use_fsdp_inference: generator.engine.use_fsdp_inference
+      dit_layerwise_offload: generator.engine.offload.dit_layerwise
+      text_encoder_cpu_offload: generator.engine.offload.text_encoder
+      image_encoder_cpu_offload: generator.engine.offload.image_encoder
+      vae_cpu_offload: generator.engine.offload.vae
+      pin_cpu_memory: generator.engine.offload.pin_cpu_memory
+      enable_torch_compile: generator.engine.compile.enabled
+      torch_compile_kwargs: generator.engine.compile.backend,fullgraph,mode,dynamic,extras
+      disable_autocast: generator.engine.disable_autocast
+      enable_stage_verification: generator.engine.enable_stage_verification
+      prompt_txt: request.inputs.prompt_path
+      override_text_encoder_safetensors: generator.pipeline.components.text_encoder_weights
+      override_text_encoder_quant: generator.engine.quantization.text_encoder_quant
+      override_transformer_cls_name: generator.pipeline.components.override_transformer_cls_name
+      init_weights_from_safetensors: generator.pipeline.components.transformer_weights
+      init_weights_from_safetensors_2: generator.pipeline.components.transformer_2_weights
+      override_pipeline_cls_name: generator.pipeline.components.override_pipeline_cls_name
+      boundary_ratio: request.sampling.boundary_ratio
+      ltx2_vae_tiling: generator.pipeline.vae_tiling
+    preset_owned:
+      ltx2_vae_spatial_tile_size_in_pixels: generator.pipeline.preset_overrides.ltx2.vae.spatial_tile_size_in_pixels
+      ltx2_vae_spatial_tile_overlap_in_pixels: generator.pipeline.preset_overrides.ltx2.vae.spatial_tile_overlap_in_pixels
+      ltx2_vae_temporal_tile_size_in_frames: generator.pipeline.preset_overrides.ltx2.vae.temporal_tile_size_in_frames
+      ltx2_vae_temporal_tile_overlap_in_frames: generator.pipeline.preset_overrides.ltx2.vae.temporal_tile_overlap_in_frames
+      ltx2_initial_latent_path: request.extensions.ltx2.initial_latent_path
+    compatibility_only:
+      mode: "Legacy multi-mode FastVideoArgs switch; typed inference config should not expose execution mode."
+      inference_mode: "Legacy boolean mirror of mode; kept only through adapters while FastVideoArgs remains."
+      lora_nickname: "Legacy adapter-selection surface pending LoRA API cleanup."
+      lora_target_modules: "Legacy LoRA configuration surface pending dedicated component API."
+      output_type: "Legacy output formatting surface pending GenerationResult cleanup."
+      VSA_sparsity: "Model-specific inference optimization not yet represented in the typed public schema."
+      moba_config_path: "Model-specific MoBA optimization surface not yet represented in the typed public schema."
+      master_port: "Executor/bootstrap compatibility field; not part of the canonical inference schema."
+    private_only:
+      ray_placement_group: "Ray deployment-only field."
+      ray_runtime_env: "Ray deployment-only field."
+    internal_only:
+      pipeline_config: "Legacy internal carrier object."
+      preprocess_config: "Legacy preprocess carrier object."
+      moba_config: "Derived runtime config loaded from moba_config_path."
+      model_paths: "Runtime bookkeeping."
+      model_loaded: "Runtime bookkeeping."
+
+  pipeline_config_base:
+    moved:
+      pipeline_config_path: generator.pipeline.components.pipeline_config_path
+    preset_owned:
+      embedded_cfg_scale: generator.pipeline.preset_overrides.embedded_cfg_scale
+      flow_shift: generator.pipeline.preset_overrides.flow_shift
+      flow_shift_sr: generator.pipeline.preset_overrides.flow_shift_sr
+      is_causal: generator.pipeline.preset_overrides.is_causal
+      vae_tiling: generator.pipeline.preset_overrides.vae_tiling
+      vae_sp: generator.pipeline.preset_overrides.vae_sp
+      dmd_denoising_steps: generator.pipeline.preset_overrides.dmd_denoising_steps
+      ti2v_task: generator.pipeline.preset_overrides.ti2v_task
+      boundary_ratio: generator.pipeline.preset_overrides.boundary_ratio
+    compatibility_only:
+      model_path: "Redundant with generator.model_path."
+      disable_autocast: "Duplicated by generator.engine.disable_autocast during migration."
+      dit_precision: "Precision override pending dedicated typed component precision design."
+      upsampler_precision: "Precision override pending dedicated typed component precision design."
+      vae_precision: "Precision override pending dedicated typed component precision design."
+      image_encoder_precision: "Precision override pending dedicated typed component precision design."
+      text_encoder_precisions: "Precision override pending dedicated typed component precision design."
+    internal_only:
+      dit_config: "Legacy internal component config object."
+      upsampler_config: "Legacy internal component config object."
+      vae_config: "Legacy internal component config object."
+      image_encoder_config: "Legacy internal component config object."
+      text_encoder_configs: "Legacy internal component config object."
+      preprocess_text_funcs: "Internal text preprocessing hooks."
+      postprocess_text_funcs: "Internal text postprocessing hooks."
+
+  pipeline_config_extensions:
+    preset_owned:
+      conditioning_strategy:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      max_num_conditional_frames:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      min_num_conditional_frames:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      sigma_conditional:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      sigma_data:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      state_ch:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      state_t:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      text_encoder_class:
+        sources:
+          - fastvideo.configs.pipelines.cosmos.CosmosConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      autoregressive_chunk_frames:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      autoregressive_overlap_frames:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      cfg_behavior:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      default_camera_rotation:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      default_movement_distance:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      default_negative_prompt:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      default_trajectory_type:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      filter_points_threshold:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      fps:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      frame_buffer_max:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      moge_model_name:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      noise_aug_strength:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      num_frames:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      offload_moge_after_depth:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      use_moge_depth:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      video_resolution:
+        sources:
+          - fastvideo.configs.pipelines.gen3c.Gen3CConfig
+          - fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
+      text_encoder_crop_start:
+        sources:
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V480PStepDistilledConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V720PConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15SR1080PConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V480PConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V720PConfig
+          - fastvideo.configs.pipelines.hyworld.HYWorldConfig
+          - fastvideo.configs.pipelines.hyworld.Hunyuan15T2V480PConfig
+      text_encoder_max_lengths:
+        sources:
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V480PStepDistilledConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V720PConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15SR1080PConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V480PConfig
+          - fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V720PConfig
+          - fastvideo.configs.pipelines.hyworld.HYWorldConfig
+          - fastvideo.configs.pipelines.hyworld.Hunyuan15T2V480PConfig
+      precision:
+        sources:
+          - fastvideo.configs.pipelines.lingbotworld.LingBotWorldI2V480PConfig
+          - fastvideo.configs.pipelines.lingbotworld.Wan2_2_I2V_A14B_Config
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2VConfig
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2V_A14B_Config
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2VConfig
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_14B_Config
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_1_3B_Config
+          - fastvideo.configs.pipelines.wan.FastWan2_1_T2V_480P_Config
+          - fastvideo.configs.pipelines.wan.FastWan2_2_TI2V_5B_Config
+          - fastvideo.configs.pipelines.wan.MatrixGameBaseI2V480PConfig
+          - fastvideo.configs.pipelines.wan.MatrixGameI2V480PConfig
+          - fastvideo.configs.pipelines.wan.SelfForcingWan2_2_T2V480PConfig
+          - fastvideo.configs.pipelines.wan.SelfForcingWanT2V480PConfig
+          - fastvideo.configs.pipelines.wan.WANV2VConfig
+          - fastvideo.configs.pipelines.wan.Wan2_2_I2V_A14B_Config
+          - fastvideo.configs.pipelines.wan.Wan2_2_T2V_A14B_Config
+          - fastvideo.configs.pipelines.wan.Wan2_2_TI2V_5B_Config
+          - fastvideo.configs.pipelines.wan.WanI2V480PConfig
+          - fastvideo.configs.pipelines.wan.WanI2V720PConfig
+          - fastvideo.configs.pipelines.wan.WanT2V480PConfig
+          - fastvideo.configs.pipelines.wan.WanT2V720PConfig
+      warp_denoising_step:
+        sources:
+          - fastvideo.configs.pipelines.lingbotworld.LingBotWorldI2V480PConfig
+          - fastvideo.configs.pipelines.lingbotworld.Wan2_2_I2V_A14B_Config
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2VConfig
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2V_A14B_Config
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2VConfig
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_14B_Config
+          - fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_1_3B_Config
+          - fastvideo.configs.pipelines.wan.FastWan2_1_T2V_480P_Config
+          - fastvideo.configs.pipelines.wan.FastWan2_2_TI2V_5B_Config
+          - fastvideo.configs.pipelines.wan.MatrixGameBaseI2V480PConfig
+          - fastvideo.configs.pipelines.wan.MatrixGameI2V480PConfig
+          - fastvideo.configs.pipelines.wan.SelfForcingWan2_2_T2V480PConfig
+          - fastvideo.configs.pipelines.wan.SelfForcingWanT2V480PConfig
+          - fastvideo.configs.pipelines.wan.WANV2VConfig
+          - fastvideo.configs.pipelines.wan.Wan2_2_I2V_A14B_Config
+          - fastvideo.configs.pipelines.wan.Wan2_2_T2V_A14B_Config
+          - fastvideo.configs.pipelines.wan.Wan2_2_TI2V_5B_Config
+          - fastvideo.configs.pipelines.wan.WanI2V480PConfig
+          - fastvideo.configs.pipelines.wan.WanI2V720PConfig
+          - fastvideo.configs.pipelines.wan.WanT2V480PConfig
+          - fastvideo.configs.pipelines.wan.WanT2V720PConfig
+      bsa_cdf_threshold:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      bsa_chunk_k:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      bsa_chunk_q:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      bsa_params:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      bsa_sparsity:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      enable_bsa:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      enable_kv_cache:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      enhance_hf:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      offload_kv_cache:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      t_thresh:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      use_distill:
+        sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
+      scheduler_arch:
+        sources: [fastvideo.configs.pipelines.sd35.SD35Config]
+      text_encoder_archs:
+        sources: [fastvideo.configs.pipelines.sd35.SD35Config]
+      tokenizer_archs:
+        sources: [fastvideo.configs.pipelines.sd35.SD35Config]
+      transformer_arch:
+        sources: [fastvideo.configs.pipelines.sd35.SD35Config]
+      vae_arch:
+        sources: [fastvideo.configs.pipelines.sd35.SD35Config]
+      expand_timesteps:
+        sources:
+          - fastvideo.configs.pipelines.wan.FastWan2_2_TI2V_5B_Config
+          - fastvideo.configs.pipelines.wan.Wan2_2_TI2V_5B_Config
+      context_noise:
+        sources: [fastvideo.configs.pipelines.wan.MatrixGameI2V480PConfig]
+      num_frames_per_block:
+        sources: [fastvideo.configs.pipelines.wan.MatrixGameI2V480PConfig]
+      audio_channels:
+        sources:
+          - fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
+          - fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
+      audio_end_in_s:
+        sources:
+          - fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
+          - fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
+      audio_start_in_s:
+        sources:
+          - fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
+          - fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
+      max_audio_duration_s:
+        sources:
+          - fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
+          - fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
+      sample_size:
+        sources:
+          - fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
+          - fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
+      sampling_rate:
+        sources:
+          - fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
+          - fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
+    compatibility_only:
+      batch_size: "Gen3C inference-only tuning field pending typed batching design."
+      gradient_checkpointing: "Gen3C inference-only compatibility field pending typed batching design."
+      guidance_scale: "Gen3C pipeline-level default pending preset/default-request cleanup."
+      num_inference_steps: "Gen3C pipeline-level default pending preset/default-request cleanup."
+    internal_only:
+      audio_decoder_config: "Legacy internal component config object."
+      audio_decoder_precision: "Precision override pending dedicated component precision design."
+      vocoder_config: "Legacy internal component config object."
+      vocoder_precision: "Precision override pending dedicated component precision design."
+
+  sampling_param_base:
+    moved:
+      image_path: request.inputs.image_path
+      pil_image: request.inputs.pil_image
+      video_path: request.inputs.video_path
+      mouse_cond: request.inputs.mouse_cond
+      keyboard_cond: request.inputs.keyboard_cond
+      grid_sizes: request.inputs.grid_sizes
+      pose: request.inputs.pose
+      c2ws_plucker_emb: request.inputs.c2ws_plucker_emb
+      refine_from: request.inputs.refine_from
+      stage1_video: request.inputs.stage1_video
+      prompt: request.prompt
+      negative_prompt: request.negative_prompt
+      prompt_path: request.inputs.prompt_path
+      output_path: request.output.output_path
+      output_video_name: request.output.output_video_name
+      num_videos_per_prompt: request.sampling.num_videos_per_prompt
+      seed: request.sampling.seed
+      num_frames: request.sampling.num_frames
+      height: request.sampling.height
+      width: request.sampling.width
+      height_sr: request.sampling.height_sr
+      width_sr: request.sampling.width_sr
+      fps: request.sampling.fps
+      num_inference_steps: request.sampling.num_inference_steps
+      num_inference_steps_sr: request.sampling.num_inference_steps_sr
+      guidance_scale: request.sampling.guidance_scale
+      guidance_scale_2: request.sampling.guidance_scale_2
+      guidance_rescale: request.sampling.guidance_rescale
+      boundary_ratio: request.sampling.boundary_ratio
+      sigmas: request.sampling.sigmas
+      enable_teacache: request.runtime.enable_teacache
+      save_video: request.output.save_video
+      return_frames: request.output.return_frames
+      return_trajectory_latents: request.runtime.return_trajectory_latents
+      return_trajectory_decoded: request.runtime.return_trajectory_decoded
+      continuation_state: request.state
+      return_continuation_state: request.output.return_state
+    preset_owned:
+      t_thresh: request.stage_overrides.refine.t_thresh
+      spatial_refine_only: request.stage_overrides.refine.spatial_refine_only
+      num_cond_frames: request.stage_overrides.refine.num_cond_frames
+      trajectory_type: request.extensions.gen3c.trajectory_type
+      movement_distance: request.extensions.gen3c.movement_distance
+      camera_rotation: request.extensions.gen3c.camera_rotation
+      prompt_attention_mask: request.extensions.hyworld.prompt_attention_mask
+      negative_attention_mask: request.extensions.hyworld.negative_attention_mask
+      camera_states: request.extensions.hunyuangamecraft.camera_states
+      camera_trajectory: request.extensions.hunyuangamecraft.camera_trajectory
+      action_list: request.extensions.hunyuangamecraft.action_list
+      action_speed_list: request.extensions.hunyuangamecraft.action_speed_list
+      gt_latents: request.extensions.hunyuangamecraft.gt_latents
+      conditioning_mask: request.extensions.hunyuangamecraft.conditioning_mask
+      ltx2_cfg_scale_video: request.extensions.ltx2.cfg_scale_video
+      ltx2_cfg_scale_audio: request.extensions.ltx2.cfg_scale_audio
+      ltx2_modality_scale_video: request.extensions.ltx2.modality_scale_video
+      ltx2_modality_scale_audio: request.extensions.ltx2.modality_scale_audio
+      ltx2_rescale_scale: request.extensions.ltx2.rescale_scale
+      ltx2_stg_scale_video: request.extensions.ltx2.stg_scale_video
+      ltx2_stg_scale_audio: request.extensions.ltx2.stg_scale_audio
+      ltx2_stg_blocks_video: request.extensions.ltx2.stg_blocks_video
+      ltx2_stg_blocks_audio: request.extensions.ltx2.stg_blocks_audio
+      audio_start_in_s: request.extensions.stable_audio.audio_start_in_s
+      audio_end_in_s: request.extensions.stable_audio.audio_end_in_s
+      init_audio: request.extensions.stable_audio.init_audio
+      init_audio_strength: request.extensions.stable_audio.init_audio_strength
+      init_noise_level: request.extensions.stable_audio.init_noise_level
+      inpaint_audio: request.extensions.stable_audio.inpaint_audio
+      inpaint_mask: request.extensions.stable_audio.inpaint_mask
+    internal_only:
+      data_type: "Derived from the request shape and not a public input."
+
+  sampling_param_extensions: {}
+
+  openai_image_request:
+    kept:
+      model: "HTTP adapter model-routing field."
+      response_format: "HTTP adapter response formatting field."
+      output_format: "HTTP adapter output-format field."
+      background: "HTTP adapter output-format field."
+      quality: "Compatibility field currently accepted by the adapter."
+      style: "Compatibility field currently accepted by the adapter."
+      user: "Compatibility field currently accepted by the adapter."
+    moved:
+      prompt: request.prompt
+      n: request.sampling.num_videos_per_prompt
+      size:
+        target: request.sampling.width,height
+        note: "Adapter parses OpenAI size strings as WIDTHxHEIGHT and forwards width then height."
+      num_inference_steps: request.sampling.num_inference_steps
+      guidance_scale: request.sampling.guidance_scale
+      true_cfg_scale: request.sampling.true_cfg_scale
+      seed: request.sampling.seed
+      negative_prompt: request.negative_prompt
+      enable_teacache: request.runtime.enable_teacache
+
+  openai_video_request:
+    kept:
+      model: "HTTP adapter model-routing field."
+    moved:
+      prompt: request.prompt
+      input_reference: request.inputs.image_path
+      reference_url: request.inputs.image_path
+      size:
+        target: request.sampling.width,height
+        note: "Adapter parses OpenAI size strings as WIDTHxHEIGHT and forwards width then height."
+      fps: request.sampling.fps
+      num_frames: request.sampling.num_frames
+      seed: request.sampling.seed
+      num_inference_steps: request.sampling.num_inference_steps
+      guidance_scale: request.sampling.guidance_scale
+      guidance_scale_2: request.sampling.guidance_scale_2
+      true_cfg_scale: request.sampling.true_cfg_scale
+      negative_prompt: request.negative_prompt
+      enable_teacache: request.runtime.enable_teacache
+      output_path: request.output.output_path
+    compatibility_only:
+      seconds:
+        target: request.sampling.num_frames
+        note: "HTTP adapter duration convenience field. If num_frames is omitted, the adapter computes num_frames = fps * seconds."
+
+cli:
+  notes:
+    - "CLI parity is checked against the actual generate/serve parser dest sets."
+    - "The inventory tracks parser dest names, excluding argparse's implicit help action."
+    - "The refactored inference CLI is config-only: subcommands expose only --config, and any additional CLI input must use dotted override paths."
+  generate:
+    explicit_local_fields:
+      - config
+    expected_dests:
+      - config
+  serve:
+    explicit_local_fields:
+      - config
+    expected_dests:
+      - config

docs/design/overview.md

@@ -12,7 +12,7 @@ FastVideo maps a Diffusers-style repo into a pipeline like this:
 - `fastvideo/configs/models/*`: arch configs and `param_names_mapping` for
   weight name translation.
 - `fastvideo/configs/pipelines/*`: pipeline wiring (component classes + names).
-- `fastvideo/configs/sample/*`: default runtime sampling parameters.
+- `fastvideo/api/sampling_param.py`: runtime sampling parameters.
 - `fastvideo/pipelines/basic/*`: end-to-end pipelines.
 - `fastvideo/pipelines/stages/*`: reusable pipeline stages.
 - `fastvideo/models/loader/*`: component loaders for Diffusers-style repos.
@@ -26,7 +26,7 @@ Minimal usage (from `examples/inference/basic/basic.py`):
 
 ```python
 from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
+from fastvideo.api.sampling_param import SamplingParam
 
 model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"  # or official_weights/<model_name>/
 generator = VideoGenerator.from_pretrained(model_id, num_gpus=1)
@@ -49,8 +49,9 @@ runtime parameters consistent:
 - `fastvideo/configs/models/`: architecture definitions, layer shapes, and
   `param_names_mapping` rules for key renaming.
 - `fastvideo/configs/pipelines/`: pipeline wiring and required components.
-- `fastvideo/configs/sample/`: default sampling parameters (steps, frames,
-  guidance scale, resolution, fps).
+- `fastvideo/api/sampling_param.py`: sampling parameters (steps, frames,
+  guidance scale, resolution, fps). Defaults come from profiles in
+  `fastvideo/pipelines/basic/<family>/profiles.py`.
 - `fastvideo/registry.py`: unified registry for pipeline config + sampling
   defaults and model metadata resolution, defined via explicit
   `register_configs(...)` blocks (no separate dict registries).
@@ -142,7 +143,7 @@ How this maps to FastVideo:
 - `T5TokenizerFast` -> loaded via HF in `fastvideo/models/loader/`
 - `UniPCMultistepScheduler` -> loaded via Diffusers scheduler utilities
 - Pipeline defaults -> `fastvideo/configs/pipelines/wan.py`
-- Sampling defaults -> `fastvideo/configs/sample/wan.py`
+- Sampling defaults -> `fastvideo/pipelines/basic/wan/profiles.py`
 
 ## Pipeline system
 

docs/design/server_contracts/streaming.md

@@ -0,0 +1,177 @@
+# Streaming WebSocket Server Contract
+
+The streaming server (`fastvideo/entrypoints/streaming/server.py`) speaks
+a JSON-over-WebSocket protocol with binary fMP4 chunks for media. This
+document is the authoritative spec for the message catalogue and the
+session state machine. Any change to either must update this document
+in the same PR that touches `protocol.py` or `session.py`.
+
+## Endpoint
+
+| Path | Protocol | Purpose |
+|---|---|---|
+| `WS /v1/stream` | WebSocket (JSON + binary) | Per-session realtime streaming |
+| `GET /health` | HTTP | Liveness probe (`status`, `stream_mode`, active `sessions`) |
+
+The server is launched by `fastvideo serve --config <serve.yaml>` when
+the config carries a `streaming:` block. Without that block the same CLI
+launches the OpenAI stateless HTTP server instead.
+
+## Connection lifecycle
+
+Every WebSocket connection holds exactly one `Session`. Sessions move
+through the states in `SessionState` (`fastvideo/entrypoints/streaming/session.py`).
+
+```
+                    ┌──────────────┐
+                    │ INITIALIZING │  ← WebSocket accepted, before init frame
+                    └──────┬───────┘
+                           │ session_init_v2 received
+            ┌──────────────┼──────────────┐
+            ▼              ▼              ▼
+         QUEUED      GPU_BINDING       REJECTED
+            │              │              ↑
+            │ slot ready   │              │ max-sessions hit
+            ▼              ▼              │ or invalid init
+                       ┌────────┐         │
+                       │ ACTIVE │ ────────┘
+                       └────┬───┘
+              segment loop  │
+                            │
+                ┌───────────┼───────────┐
+                ▼           ▼           ▼
+            COMPLETE      ERROR      TIMEOUT
+        (clean leave)  (any failure)  (idle / segment_cap reached)
+```
+
+Terminal states (`COMPLETE`, `ERROR`, `TIMEOUT`, `REJECTED`) are sinks —
+no transitions out. The transition matrix is enforced in
+`session.py::_VALID_TRANSITIONS`; bad transitions raise.
+
+`SessionManager` enforces the per-process budgets pulled from
+`StreamingConfig`:
+
+- `session_timeout_seconds` — idle reaper drops sessions that haven't
+  advanced; non-terminal sessions transition to `TIMEOUT`.
+- `generation_segment_cap` — a session that hits the cap transitions to
+  `COMPLETE` after the last segment ships.
+
+## Message catalogue
+
+Every JSON frame carries `{"type": <str>, ...}`. Pydantic models in
+`protocol.py` are the source of truth; this table is the human-readable
+view.
+
+### Client → server
+
+| `type` | Required fields | Purpose |
+|---|---|---|
+| `session_init_v2` | — | Opening frame. Carries preset, curated prompts, optional initial image, feature toggles, optional `continuation_state` to resume from a snapshot. |
+| `segment_prompt_source` | `prompt` | Request the next segment using the supplied prompt; optional sampling overrides (`seed`, `num_inference_steps`, `guidance_scale`, `negative_prompt`). |
+| `seed_prompts_updated` | `seed_prompts` | Replace the session's seed-prompt list; takes effect on the next segment. |
+| `enhancement_updated` | `enabled` | Toggle prompt enhancement for subsequent segments. |
+| `auto_extension_updated` | `enabled` | Toggle automatic per-segment prompt extension. |
+| `loop_generation_updated` | `enabled` | Toggle loop-generation mode. |
+| `generation_paused_updated` | `paused` | Pause/resume segment generation; queued requests defer. |
+| `snapshot_state` | — | Request the current `ContinuationState` for export; server replies with `continuation_state_snapshot`. |
+
+The opening frame must be `session_init_v2`. Any other first frame is
+rejected with an `error` (code `invalid_message`) and the WebSocket is
+closed.
+
+### Server → client
+
+| `type` | Carries | When emitted |
+|---|---|---|
+| `queue_status` | `position`, `queue_depth` | After `session_init_v2` accepted, before GPU binding. |
+| `gpu_assigned` | GPU id, model id | Once a generator slot is bound. |
+| `ltx2_stream_start` | session-level metadata | Once the session enters `ACTIVE`. |
+| `ltx2_segment_start` | `segment_idx`, `prompt`, prompt source | When a `segment_prompt_source` request begins generation. |
+| `step_complete` | `segment_idx`, denoise timings | After the segment's denoising loop finishes (before media emission). |
+| `media_init` | `segment_idx`, mime, stream id | First frame of fMP4 output for the segment. |
+| binary frame | fMP4 fragment bytes | Subsequent media chunks; the protocol enforces that `media_init` precedes any binary frames. |
+| `media_segment_complete` | `segment_idx`, chunk count, byte count | Last media chunk for the segment. |
+| `ltx2_segment_complete` | `segment_idx`, segment summary | Segment fully shipped; ready for the next `segment_prompt_source`. |
+| `ltx2_stream_complete` | session summary | Session reached `generation_segment_cap` or client requested clean shutdown. |
+| `session_timeout` | reason | Session hit `session_timeout_seconds`; immediately followed by close. |
+| `continuation_state_snapshot` | `kind`, `payload` | Reply to `snapshot_state`. The payload is the same shape produced by `LTX2ContinuationState.to_continuation_state(...)`. |
+| `error` | `code`, `message` | Any validation/runtime error. Non-fatal errors keep the connection open; fatal errors precede a `close`. |
+
+## Continuation state
+
+The session optionally accepts a `continuation_state` dict inside the
+opening `session_init_v2` frame. When present, the server hydrates it
+into a `ContinuationState(kind, payload)` envelope and feeds it as the
+`request.state` on the first segment's `GenerationRequest` — letting a
+client resume after a disconnect, migrate sessions across processes,
+or replay a prior session.
+
+After every segment, if the runtime returns a fresh state, the server
+persists it to the `SessionStore` so a `snapshot_state` request can
+export it. The store and serialization contracts live with the model
+family (e.g. `fastvideo/pipelines/basic/ltx2/continuation.py` for LTX-2).
+
+## Example flow
+
+```
+client                                                    server
+──────                                                    ──────
+WS /v1/stream  ─────── connect ─────────────────────────►
+               ◄────── (accept)
+
+{"type": "session_init_v2",
+ "preset": "ltx2_two_stage",
+ "curated_prompts": ["a fox in snow", "the fox jumps"],
+ "initial_image": {...},
+ "stream_mode": "av_fmp4"} ─────────────────────────────►
+
+                                                          (validate, queue, bind)
+               ◄──── {"type": "queue_status",
+                       "position": 0, "queue_depth": 0}
+               ◄──── {"type": "gpu_assigned",
+                       "gpu_id": 0, "model_id": "..."}
+               ◄──── {"type": "ltx2_stream_start", ...}
+
+{"type": "segment_prompt_source",
+ "prompt": "a fox in snow",
+ "source": "curated"} ───────────────────────────────────►
+                                                          (run pipeline)
+               ◄──── {"type": "ltx2_segment_start",
+                       "segment_idx": 1, ...}
+               ◄──── {"type": "step_complete",
+                       "segment_idx": 1, "timings": {...}}
+               ◄──── {"type": "media_init",
+                       "segment_idx": 1,
+                       "mime": "video/mp4", ...}
+               ◄──── <binary fMP4 init segment>
+               ◄──── <binary fMP4 fragment>
+               ◄──── <binary fMP4 fragment>
+               ◄──── {"type": "media_segment_complete",
+                       "segment_idx": 1, "chunks": 12}
+               ◄──── {"type": "ltx2_segment_complete",
+                       "segment_idx": 1, ...}
+
+{"type": "segment_prompt_source",
+ "prompt": "the fox jumps"} ─────────────────────────────►
+                                                          (segment 2 …)
+
+{"type": "snapshot_state"} ──────────────────────────────►
+               ◄──── {"type": "continuation_state_snapshot",
+                       "kind": "ltx2.v1",
+                       "payload": {"schema_version": 1, ...}}
+
+(close) ──────────────────────────────────────────────────►
+                                                          (session → COMPLETE)
+```
+
+## Backward / forward compatibility
+
+- Adding a new client message: append a Pydantic model to `protocol.py`
+  with a unique `type`; add the discriminator entry to `ClientMessage`;
+  add a row to the table above. Old clients that don't send the new
+  message remain compatible.
+- Adding a new server message: emit only when a new feature flag is
+  enabled (or always emit, since clients ignore unknown types).
+- Changing an existing message: bump the `type` (e.g. `session_init_v2`
+  → `session_init_v3`) and accept both for one release cycle. Never
+  silently change field semantics under the same `type`.

docs/design/training_architecture.md

@@ -243,7 +243,7 @@ for step in range(start_step, max_steps):
 
 ```bash
 # Install
-uv pip install -e .[dev]
+uv pip install -e ".[dev]"
 
 # Run DMD2 distillation on Wan 2.1
 torchrun --nproc_per_node=8 -m fastvideo.train.entrypoint.train \

docs/distillation/dmd.md

@@ -16,7 +16,8 @@ Both models are trained on **61×448×832** resolution but support generating vi
 First install [VSA](../attention/vsa/index.md). Set `MODEL_BASE` to your own model path and run:
 
 ```bash
-bash scripts/inference/v1_inference_wan_dmd.sh
+FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN \
+  fastvideo generate --config scripts/inference/inference_wan_VSA_DMD_1_3B.yaml
 ```
 
 ## 🗂️ Dataset
@@ -85,3 +86,25 @@ sbatch examples/distill/Wan2.2-TI2V-5B-Diffusers/Data-free/distill_dmd_t2v_5B.sh
 - Learning rate: 2e-5
 - Training steps: 3000 (~12 hours)
 - HSDP shard dim: 1
+
+## 🧭 Note on `real_score_guidance_scale`
+
+The teacher CFG used inside the DMD loss follows the DMD2 reference
+implementation and uses the parameterization
+
+```
+x = x_cond + w * (x_cond - x_uncond)
+```
+
+rather than the Ho & Salimans form `x_uncond + w * (x_cond - x_uncond)`. The
+two are mathematically equivalent up to a constant offset:
+
+| `real_score_guidance_scale` (`w`) | Equivalent standard CFG (`w + 1`) | Output                |
+|-----------------------------------|-----------------------------------|-----------------------|
+| `-1`                              | `0`                               | unconditional         |
+| `0`                               | `1`                               | conditional           |
+| `3.5` (default)                   | `4.5`                             | strong guidance       |
+
+So `real_score_guidance_scale` should be read as the **extra** guidance
+strength added on top of the conditional prediction. When porting values
+from a paper that uses the Ho & Salimans form, subtract 1.

docs/generate_examples.py

@@ -42,8 +42,7 @@ def fix_case(text: str) -> str:
         r"int\d+": lambda x: x.group(0).upper(),  # e.g. int8, int16
     }
     for pattern, repl in subs.items():
-        text = re.sub(rf'\b{pattern}\b', repl, text,
-                      flags=re.IGNORECASE)  # type: ignore[call-overload]
+        text = re.sub(rf'\b{pattern}\b', repl, text, flags=re.IGNORECASE)  # type: ignore[call-overload]
     return text
 
 
@@ -134,9 +133,7 @@ class Example:
         if not markdown_files:
             raise IndexError(f"No Markdown files found in {self.path}")
 
-        readme_files = [
-            f for f in markdown_files if f.name.lower() == "readme.md"
-        ]
+        readme_files = [f for f in markdown_files if f.name.lower() == "readme.md"]
         if readme_files:
             return readme_files[0]
 
@@ -156,8 +153,7 @@ class Example:
         if self.path.is_file():
             return []
         is_other_file = lambda file: file.is_file() and file != self.main_file
-        return [file for file in self.path.rglob("*")
-                if is_other_file(file)]  # type: ignore[no-untyped-call]
+        return [file for file in self.path.rglob("*") if is_other_file(file)]  # type: ignore[no-untyped-call]
 
     def determine_title(self) -> str:
         return fix_case(self.path.stem.replace("_", " ").title())
@@ -190,8 +186,8 @@ class Example:
         content += "## Additional Files\n\n"
         # Define binary/non-text file extensions to skip
         binary_extensions = {
-            '.mp4', '.avi', '.mov', '.mkv', '.gif', '.jpg', '.jpeg', '.png',
-            '.webp', '.bmp', '.pdf', '.zip', '.tar', '.gz', '.mp3', '.wav'
+            '.mp4', '.avi', '.mov', '.mkv', '.gif', '.jpg', '.jpeg', '.png', '.webp', '.bmp', '.pdf', '.zip', '.tar',
+            '.gz', '.mp3', '.wav'
         }
 
         for file in sorted(self.other_files):
@@ -259,8 +255,7 @@ def create_category_indices() -> dict[str, Index]:
     category_indices = {
         "inference":
         Index(
-            path=ROOT_DIR /
-            "docs/inference/examples/examples_inference_index.md",
+            path=ROOT_DIR / "docs/inference/examples/examples_inference_index.md",
             title="🚀 Examples",
             description=
             "Inference examples demonstrate how to use FastVideo inference. We recommend starting with [basic.md](basic.md).",
@@ -271,18 +266,15 @@ def create_category_indices() -> dict[str, Index]:
         Index(
             path=ROOT_DIR / "docs/training/examples/examples_training_index.md",
             title="🚀 Examples",
-            description=
-            "Training examples demonstrate how to use FastVideo training.",
+            description="Training examples demonstrate how to use FastVideo training.",
             caption="Examples",
             maxdepth=3,
         ),
         "distillation":
         Index(
-            path=ROOT_DIR /
-            "docs/distillation/examples/examples_distillation_index.md",
+            path=ROOT_DIR / "docs/distillation/examples/examples_distillation_index.md",
             title="🚀 Examples",
-            description=
-            "Distillation examples demonstrate how to use FastVideo distillation.",
+            description="Distillation examples demonstrate how to use FastVideo distillation.",
             caption="Examples",
             maxdepth=3,
         ),
@@ -296,8 +288,7 @@ def create_category_indices() -> dict[str, Index]:
     return category_indices
 
 
-def find_examples(category_indices: dict[str, Index],
-                  generate_main_index: bool) -> list[Example]:
+def find_examples(category_indices: dict[str, Index], generate_main_index: bool) -> list[Example]:
     """Find all examples from the examples directory."""
     examples = []
     glob_patterns = ["*.py", "*.md", "*.sh"]
@@ -339,13 +330,9 @@ def find_examples(category_indices: dict[str, Index],
     return examples
 
 
-def create_nested_structures(
-    examples: list[Example]
-) -> dict[str, dict[str, dict[str, dict[str, NestedStructure]]]]:
+def create_nested_structures(examples: list[Example]) -> dict[str, dict[str, dict[str, dict[str, NestedStructure]]]]:
     """Create nested structures for training and distillation categories."""
-    nested_structures: dict[str, dict[str, dict[str,
-                                                dict[str,
-                                                     NestedStructure]]]] = {}
+    nested_structures: dict[str, dict[str, dict[str, dict[str, NestedStructure]]]] = {}
 
     # Map category names to actual directory names
     category_dir_mapping = {
@@ -378,13 +365,11 @@ def create_nested_structures(
                     nested_structures[example.category][method][model] = {}
 
                 # Store the nested structure
-                nested_structures[
-                    example.category][method][model][dataset] = NestedStructure(
-                        category=example.category,
-                        method=method,
-                        model=model,
-                        dataset=dataset,
-                        example=example)
+                nested_structures[example.category][method][model][dataset] = NestedStructure(category=example.category,
+                                                                                              method=method,
+                                                                                              model=model,
+                                                                                              dataset=dataset,
+                                                                                              example=example)
 
         elif example.category == "distillation" and len(path_parts) >= 2:
             # For distillation examples like Wan2.1-T2V/Wan-Syn-Data-480P
@@ -401,20 +386,16 @@ def create_nested_structures(
                 nested_structures[example.category][method][model] = {}
 
             # Store the nested structure
-            nested_structures[
-                example.category][method][model][dataset] = NestedStructure(
-                    category=example.category,
-                    method=method,
-                    model=model,
-                    dataset=dataset,
-                    example=example)
+            nested_structures[example.category][method][model][dataset] = NestedStructure(category=example.category,
+                                                                                          method=method,
+                                                                                          model=model,
+                                                                                          dataset=dataset,
+                                                                                          example=example)
 
     return nested_structures
 
 
-def generate_flat_examples(examples: list[Example],
-                           category_indices: dict[str, Index],
-                           examples_index: Index | None,
+def generate_flat_examples(examples: list[Example], category_indices: dict[str, Index], examples_index: Index | None,
                            generate_main_index: bool) -> None:
     """Generate documentation for flat structure examples (inference, etc.)."""
     for example in examples:
@@ -437,9 +418,8 @@ def generate_flat_examples(examples: list[Example],
         index.documents.append(example.path.stem)
 
 
-def generate_nested_examples(nested_structures: dict[str, dict[str, dict[
-    str, dict[str, NestedStructure]]]], category_indices: dict[str,
-                                                               Index]) -> None:
+def generate_nested_examples(nested_structures: dict[str, dict[str, dict[str, dict[str, NestedStructure]]]],
+                             category_indices: dict[str, Index]) -> None:
     """Generate documentation for nested structure examples (training, distillation)."""
     for category_name in ["training", "distillation"]:
         if category_name not in category_indices or category_name not in nested_structures:
@@ -464,12 +444,11 @@ def generate_nested_examples(nested_structures: dict[str, dict[str, dict[
                         f.write(nested_struct.example.generate())
 
                 # Create model-level index
-                model_index = Index(
-                    path=category_base_dir / f"{model}.md",
-                    title=fix_case(model.replace('_', ' ')),
-                    description=f"Examples for the {model} model.",
-                    caption=f"{fix_case(model.replace('_', ' '))} Datasets",
-                    maxdepth=1)
+                model_index = Index(path=category_base_dir / f"{model}.md",
+                                    title=fix_case(model.replace('_', ' ')),
+                                    description=f"Examples for the {model} model.",
+                                    caption=f"{fix_case(model.replace('_', ' '))} Datasets",
+                                    maxdepth=1)
 
                 # Add dataset indices to model index
                 for dataset, nested_struct in datasets.items():
@@ -508,8 +487,7 @@ def generate_examples(generate_main_index: bool = False) -> None:
         examples_index = Index(
             path=main_index_dir / "examples_index.md",
             title="💡 Examples",
-            description=
-            "A collection of examples demonstrating usage of FastVideo.\n\n"
+            description="A collection of examples demonstrating usage of FastVideo.\n\n"
             f"All documented examples are autogenerated using [generate_examples.py](https://github.com/{GITHUB_REPO}/blob/main/docs/generate_examples.py) "
             f"from examples found in the [examples](https://github.com/{GITHUB_REPO}/tree/main/examples) directory.",
             caption="Examples",
@@ -522,8 +500,7 @@ def generate_examples(generate_main_index: bool = False) -> None:
     nested_structures = create_nested_structures(examples)
 
     # Generate flat structure examples (inference, etc.)
-    generate_flat_examples(examples, category_indices, examples_index,
-                           generate_main_index)
+    generate_flat_examples(examples, category_indices, examples_index, generate_main_index)
 
     # Generate nested structure examples (training, distillation)
     generate_nested_examples(nested_structures, category_indices)
@@ -534,11 +511,8 @@ def generate_examples(generate_main_index: bool = False) -> None:
             # Add to main index if it exists
             if generate_main_index and examples_index:
                 main_index_dir = examples_index.path.parent
-                rel_path = os.path.relpath(category_index.path,
-                                           start=main_index_dir)
-                examples_index.documents.insert(
-                    0,
-                    str(rel_path).replace("\\", "/").replace(".md", ""))
+                rel_path = os.path.relpath(category_index.path, start=main_index_dir)
+                examples_index.documents.insert(0, str(rel_path).replace("\\", "/").replace(".md", ""))
 
             # Write the category index file
             with open(category_index.path, "w+") as f:

docs/getting_started/installation.md

@@ -27,7 +27,7 @@ uv pip install fastvideo
 conda create -n fastvideo python=3.12 -y
 conda activate fastvideo
 
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 ### From source
@@ -41,11 +41,11 @@ uv pip install -e .
 uv pip install flash-attn --no-build-isolation -v
 ```
 
-Alternative with Conda environment:
+Alternative with Conda environment (still drives installs through `uv`):
 
 ```bash
-pip install -e .
-pip install flash-attn --no-build-isolation -v
+uv pip install -e .
+uv pip install flash-attn --no-build-isolation -v
 ```
 
 ## Hardware Requirements

docs/getting_started/installation/gpu.md

@@ -58,14 +58,16 @@ uv pip install flash-attn --no-build-isolation -v
 
 #### With Conda environment (alternative)
 
+`uv` works inside an active conda env too, so prefer `uv pip` for the actual install:
+
 ```bash
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 Also optionally install FlashAttention:
 
 ```bash
-pip install flash-attn --no-build-isolation -v
+uv pip install flash-attn --no-build-isolation -v
 ```
 
 ### Installation from Source
@@ -87,7 +89,7 @@ uv pip install -e .
 Alternative with Conda environment:
 
 ```bash
-pip install -e .
+uv pip install -e .
 ```
 
 ### Optional Dependencies
@@ -101,7 +103,7 @@ uv pip install flash-attn --no-build-isolation -v
 Alternative with Conda environment:
 
 ```bash
-pip install flash-attn --no-build-isolation -v
+uv pip install flash-attn --no-build-isolation -v
 ```
 
 ## Set up using Docker

docs/getting_started/installation/mps.md

@@ -57,8 +57,10 @@ uv pip install fastvideo
 
 #### With Conda environment (alternative)
 
+`uv` works inside an active conda env too, so prefer `uv pip` for the actual install:
+
 ```bash
-pip install fastvideo
+uv pip install fastvideo
 ```
 
 ### Installation from Source
@@ -80,7 +82,7 @@ uv pip install -e .
 Alternative with Conda environment:
 
 ```bash
-pip install -e .
+uv pip install -e .
 ```
 
 ## Development Environment Setup

docs/getting_started/v1_api.md

@@ -33,7 +33,7 @@ The following two classes `PipelineConfig` and `SamplingParam` are used to confi
 
 ### SamplingParam
 
-::: fastvideo.configs.sample.base.SamplingParam
+::: fastvideo.api.sampling_param.SamplingParam
     options:
       show_root_heading: true
       show_source: false

docs/inference/architecture.md

@@ -128,19 +128,14 @@ Concrete hierarchy: `DiTConfig` → `DiTArchConfig`, `VAEConfig` →
 - `dump_to_json()` / `load_from_json()` — JSON persistence. Callable
   fields and `arch_config` are excluded from dumps.
 
-### SamplingParam (`fastvideo/configs/sample/`)
+### SamplingParam (`fastvideo/api/sampling_param.py`)
 
 Generation parameters separate from pipeline config. Each model family
-provides defaults:
+provides defaults via a profile (see `fastvideo/pipelines/basic/<family>/profiles.py`):
 
 ```python
-@dataclass
-class WanT2V_1_3B_SamplingParam(SamplingParam):
-    height: int = 480
-    width: int = 832
-    num_frames: int = 81
-    guidance_scale: float = 3.0
-    num_inference_steps: int = 50
+sp = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
+# sp.height == 480, sp.width == 832, sp.num_frames == 81, etc.
 ```
 
 ## Component Loading
@@ -430,9 +425,9 @@ User: generator.generate_video(prompt, ...)
    `fastvideo/configs/pipelines/<model>.py`. Set DiT/VAE/encoder configs,
    flow_shift, precision defaults.
 
-2. **Sampling param** — Create a `SamplingParam` subclass in
-   `fastvideo/configs/sample/<model>.py`. Set default height, width,
-   num_frames, guidance_scale, num_inference_steps.
+2. **Sampling param profile** — Create a profile in
+   `fastvideo/pipelines/basic/<model>/profiles.py` with default height,
+   width, num_frames, guidance_scale, num_inference_steps.
 
 3. **Register configs** — In `fastvideo/registry.py`, add a
    `register_configs()` call inside `_register_configs()` with
@@ -455,6 +450,6 @@ User: generator.generate_video(prompt, ...)
    `fastvideo/pipelines/stages/`, implement `forward()`, optionally
    implement `verify_input()`/`verify_output()`.
 
-7. **Verify** — Run `fastvideo generate --model-path <path> --prompt
-   "test" --num-inference-steps 2` to confirm the pipeline loads and
-   generates output.
+7. **Verify** — Run `fastvideo generate --config <config.yaml>` with a
+   minimal nested config to confirm the pipeline loads and generates
+   output.

docs/inference/cli.md

@@ -1,71 +1,29 @@
 # FastVideo CLI Inference
 
-The FastVideo CLI exposes the same core inference controls as the Python API.
+The FastVideo CLI is config-first. Inference runs are driven by a nested JSON or
+YAML config, with optional dotted-path overrides on the command line. The
+contract matches training: use an explicit subcommand plus `--config`, then add
+any dotted overrides you need.
 
 ## Basic Usage
 
-Use either:
-
-1. `--model-path` + `--prompt`
-2. `--model-path` + `--prompt-txt` (batch prompts, one line per prompt)
-3. `--config` (JSON/YAML)
-
 ```bash
-fastvideo generate --model-path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
-  --prompt "A cat playing with a ball of yarn"
+fastvideo generate --config config.yaml
+fastvideo serve --config serve.yaml
 ```
 
-```bash
-fastvideo generate --model-path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
-  --prompt-txt prompts.txt
-```
-
-You cannot provide both `--prompt` and `--prompt-txt` in the same run.
-
 ## View All Arguments
 
 ```bash
 fastvideo generate --help
 ```
 
-Arguments come from:
+The subcommands intentionally expose only `--config`. Any per-run CLI changes
+must use dotted override paths such as:
 
-- FastVideo runtime args (`FastVideoArgs`)
-- Sampling args (`SamplingParam`)
-- Pipeline config args (`PipelineConfig`)
-
-## Common Arguments
-
-### Parallelism
-
-- `--num-gpus`
-- `--sp-size`
-- `--tp-size`
-
-### Sampling
-
-- `--num-frames`
-- `--height` / `--width`
-- `--num-inference-steps`
-- `--guidance-scale`
-- `--seed`
-- `--negative-prompt`
-
-### Output
-
-- `--output-path`
-- `--save-video` / `--no-save-video`
-- `--return-frames`
-
-### Offloading and Performance
-
-- `--dit-layerwise-offload`
-- `--use-fsdp-inference`
-- `--text-encoder-cpu-offload`
-- `--image-encoder-cpu-offload`
-- `--vae-cpu-offload`
-- `--enable-torch-compile`
-- `--torch-compile-kwargs`
+- `--generator.engine.num_gpus 2`
+- `--request.sampling.seed 42`
+- `--server.port 9000`
 
 ## Using Config Files
 
@@ -73,50 +31,53 @@ Arguments come from:
 fastvideo generate --config config.yaml
 ```
 
-Config files can be JSON or YAML. CLI flags override config-file values.
+Config files can be JSON or YAML. Dotted CLI overrides take precedence over
+config-file values.
 
 Example `config.yaml`:
 
 ```yaml
-model_path: "FastVideo/FastHunyuan-diffusers"
-prompt: "A capybara lounging in a hammock"
-output_path: "outputs/"
-num_gpus: 2
-sp_size: 2
-tp_size: 1
-num_frames: 45
-height: 720
-width: 1280
-num_inference_steps: 6
-seed: 1024
-dit_precision: "bf16"
-vae_precision: "fp16"
-vae_tiling: true
-vae_sp: true
-enable_torch_compile: false
+generator:
+  model_path: FastVideo/FastHunyuan-diffusers
+  engine:
+    num_gpus: 2
+    parallelism:
+      sp_size: 2
+      tp_size: 1
+request:
+  prompt: A capybara lounging in a hammock
+  sampling:
+    num_frames: 45
+    height: 720
+    width: 1280
+    num_inference_steps: 6
+    seed: 1024
+  output:
+    output_path: outputs/
 ```
 
 Notes:
 
-- Use `dit_precision` / `vae_precision` (not `precision`).
-- Nested config objects are supported, for example `vae_config` and
-  `dit_config`.
+- `generator` and `request` are the top-level keys for generation configs.
+- `serve` configs use `generator`, `server`, and optional `default_request`.
+- Prompt text files belong under `request.inputs.prompt_path`.
 
 ## Examples
 
 Simple generation:
 
 ```bash
-fastvideo generate \
-  --model-path FastVideo/FastHunyuan-diffusers \
-  --prompt "A cat playing with a ball of yarn" \
-  --num-frames 45 --height 720 --width 1280 \
-  --num-inference-steps 6 --seed 1024 \
-  --output-path outputs/
+fastvideo generate --config config.yaml
 ```
 
-Config + CLI override:
+Config + dotted override:
 
 ```bash
-fastvideo generate --config config.yaml --prompt "A panda skiing at sunset"
+fastvideo generate --config config.yaml --request.prompt "A panda skiing at sunset"
+```
+
+Helper wrapper with positional config path:
+
+```bash
+bash scripts/inference/run.sh scripts/inference/inference_wan.yaml
 ```

docs/inference/configuration.md

@@ -73,32 +73,40 @@ if __name__ == '__main__':
 
 ## JSON/YAML Config Files (CLI)
 
-The CLI supports `--config` with JSON or YAML. Command-line arguments override
-config file values.
-By default, `fastvideo generate` uses `return_frames=false` unless you set
-`--return-frames` (or `return_frames: true` in config).
+The inference CLI is config-first. Use an explicit subcommand with `--config`,
+then apply optional dotted overrides on top, matching the training CLI style.
+By default, CLI generation uses `return_frames=false` unless you set
+`request.output.return_frames: true` in config or via a dotted override.
 
 ```bash
 fastvideo generate --config config.yaml
 ```
 
-Use CLI argument names as keys (underscore or hyphen is accepted). Example:
+Example nested config:
 
 ```yaml
-model_path: "FastVideo/FastHunyuan-diffusers"
-prompt: "A capybara relaxing in a hammock"
-num_gpus: 2
-sp_size: 2
-num_frames: 45
-height: 720
-width: 1280
-num_inference_steps: 6
-seed: 1024
-dit_precision: "bf16"
-vae_precision: "fp16"
-vae_tiling: true
-vae_sp: true
-enable_torch_compile: false
+generator:
+  model_path: FastVideo/FastHunyuan-diffusers
+  engine:
+    num_gpus: 2
+    parallelism:
+      sp_size: 2
+request:
+  prompt: A capybara relaxing in a hammock
+  sampling:
+    num_frames: 45
+    height: 720
+    width: 1280
+    num_inference_steps: 6
+    seed: 1024
+  output:
+    output_path: outputs/
+```
+
+Override individual values from the CLI with dotted paths:
+
+```bash
+fastvideo generate --config config.yaml --request.sampling.seed 42
 ```
 
 ## Performance Optimization

docs/inference/gen3c.md

@@ -0,0 +1,129 @@
+# GEN3C: 3D-Informed Camera-Controlled Video Generation
+
+[GEN3C](https://arxiv.org/abs/2503.03751) is NVIDIA's Cosmos-7B-based video model for camera-controlled generation from a single image. The FastVideo integration supports the GEN3C I2V workflow, including 3D cache conditioning and tokenizer-based conditioning latents.
+
+## Key Features
+
+- **Camera trajectory control**: `left/right/up/down/zoom_in/zoom_out/clockwise/counterclockwise`
+- **3D cache conditioning**: depth prediction -> point cloud cache -> forward warping -> latent conditioning
+- **Single-image to video generation**: 121-frame generation with camera motion
+- **Official raw checkpoint conversion**: `model.pt` -> Diffusers/FastVideo layout
+
+## Model Sources
+
+- Official raw checkpoint (not Diffusers): `nvidia/GEN3C-Cosmos-7B`
+- Diffusers-format checkpoint: `FastVideo/GEN3C-Cosmos-7B-Diffusers`
+
+## Prerequisites
+
+- Install MoGe:
+
+```bash
+uv pip install git+https://github.com/microsoft/MoGe.git
+```
+
+- If you hit `ImportError: libGL.so.1` (common on Ubuntu/headless nodes), you can try installing OpenCV runtime libs:
+
+```bash
+sudo apt-get update
+sudo apt-get install -y libgl1 libglib2.0-0 libsm6 libxext6 libxrender1
+```
+
+## Quick Start
+
+### Option A: Use Diffusers-format weights directly
+
+```bash
+python examples/inference/basic/basic_gen3c.py \
+  --model_path FastVideo/GEN3C-Cosmos-7B-Diffusers \
+  --image_path /path/to/input.png \
+  --prompt "" \
+  --trajectory left \
+  --movement_distance 0.3 \
+  --camera_rotation center_facing \
+  --num_inference_steps 35 \
+  --guidance_scale 1.0 \
+  --output_path outputs_video/gen3c_output.mp4
+```
+
+### Option B: Convert official raw checkpoint locally
+
+1. Download:
+
+```bash
+huggingface-cli download nvidia/GEN3C-Cosmos-7B --local-dir official_weights/GEN3C-Cosmos-7B
+```
+
+1. Convert:
+
+```bash
+python scripts/checkpoint_conversion/convert_gen3c_to_fastvideo.py \
+  --source official_weights/GEN3C-Cosmos-7B/model.pt \
+  --output converted_weights/GEN3C-Cosmos-7B
+```
+
+1. Run:
+
+```bash
+python examples/inference/basic/basic_gen3c.py \
+  --model_path converted_weights/GEN3C-Cosmos-7B \
+  --image_path /path/to/input.png \
+  --prompt "" \
+  --trajectory left \
+  --movement_distance 0.3 \
+  --camera_rotation center_facing \
+  --num_inference_steps 35 \
+  --guidance_scale 1.0 \
+  --output_path outputs_video/gen3c_output.mp4
+```
+
+## FastVideo Defaults
+
+GEN3C defaults in FastVideo:
+
+- `height=704`, `width=1280`
+- `num_frames=121`
+- `num_inference_steps=35`
+- `guidance_scale=1.0`
+- `fps=24`
+
+These values are defined in:
+
+- `fastvideo/pipelines/basic/gen3c/profiles.py`
+- `fastvideo/configs/pipelines/gen3c.py`
+
+and align with the official GEN3C inference defaults in:
+
+- `tmp/GEN3C/cosmos_predict1/diffusion/inference/inference_utils.py`
+
+## Scheduler Note
+
+The converted GEN3C Diffusers layout may include a FlowMatch scheduler config, but GEN3C denoising uses EDM preconditioning behavior. FastVideo's GEN3C pipeline enforces an EDM scheduler at runtime for parity with official inference behavior.
+
+Implementation path:
+
+- `fastvideo/pipelines/basic/gen3c/gen3c_pipeline.py`
+
+## 3D Cache Conditioning Path
+
+FastVideo GEN3C conditioning stage performs:
+
+1. MoGe depth estimation from input image
+2. 3D cache initialization
+3. Camera trajectory generation
+4. Forward rendering of warped frames + masks
+5. VAE/tokenizer encoding of conditioning buffers
+6. Denoising with condition mask + condition pose channels
+
+Main implementation:
+
+- `fastvideo/pipelines/basic/gen3c/gen3c_pipeline.py`
+- `fastvideo/pipelines/basic/gen3c/cache_3d.py`
+- `fastvideo/pipelines/basic/gen3c/depth_estimation.py`
+- `fastvideo/models/vaes/gen3c_tokenizer_vae.py`
+
+## References
+
+- [GEN3C Paper](https://arxiv.org/abs/2503.03751)
+- [Official Repository](https://github.com/nv-tlabs/GEN3C)
+- [Official Checkpoint (raw)](https://huggingface.co/nvidia/GEN3C-Cosmos-7B)

docs/inference/optimizations.md

@@ -54,7 +54,7 @@ FASTVIDEO_ATTENTION_BACKEND=SAGE_ATTN python example.py
 We recommend always installing [Flash Attention 2](https://github.com/Dao-AILab/flash-attention):
 
 ```bash
-pip install flash-attn==2.7.4.post1 --no-build-isolation
+uv pip install flash-attn==2.7.4.post1 --no-build-isolation
 ```
 
 And if using a Hopper+ GPU (ie H100), installing [Flash Attention 3](https://github.com/Dao-AILab/flash-attention?tab=readme-ov-file#flashattention-3-beta-release) by compiling it from source (takes about 10 minutes for me):
@@ -63,7 +63,7 @@ And if using a Hopper+ GPU (ie H100), installing [Flash Attention 3](https://git
 git clone https://github.com/Dao-AILab/flash-attention.git && cd flash-attention
 
 cd hopper
-pip install ninja
+uv pip install ninja
 python setup.py install
 ```
 
@@ -98,7 +98,7 @@ To use [SageAttention](https://github.com/thu-ml/SageAttention) 2.1.1, please co
 ```bash
 git clone https://github.com/thu-ml/SageAttention.git
 cd sageattention
-python setup.py install  # or pip install -e .
+python setup.py install  # or uv pip install -e .
 ```
 
 ### Sage Attention 3

docs/inference/support_matrix.md

@@ -73,6 +73,7 @@ pipeline initialization and sampling.
 | Matrix Game 2.0 Base | `FastVideo/Matrix-Game-2.0-Base-Diffusers` | 352x640 | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
 | Matrix Game 2.0 GTA | `FastVideo/Matrix-Game-2.0-GTA-Diffusers` | 352x640 | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
 | Matrix Game 2.0 TempleRun | `FastVideo/Matrix-Game-2.0-TempleRun-Diffusers` | 352x640 | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
+| GEN3C Cosmos 7B | `FastVideo/GEN3C-Cosmos-7B-Diffusers` | 704px1280p | ❌ | ❌ | ❌ | ⭕ | ⭕ |
 
 **Note**: Wan2.2 TI2V 5B has some quality issues when performing I2V generation. We are working on fixing this issue.
 
@@ -85,6 +86,11 @@ The authoritative source for model-ID recognition is
 `fastvideo/registry.py`. If a model ID is registered there, FastVideo can
 resolve default pipeline and sampling configuration for it.
 
+**Note (GEN3C)**: The official `nvidia/GEN3C-Cosmos-7B` repo provides a raw
+`model.pt` checkpoint. Use a Diffusers-format repo (for example,
+`FastVideo/GEN3C-Cosmos-7B-Diffusers`) or convert locally with
+`scripts/checkpoint_conversion/convert_gen3c_to_fastvideo.py`.
+
 ## Special requirements
 
 ### Sliding Tile Attention

examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P/README.md

@@ -4,7 +4,7 @@ These are end-to-end example scripts for distilling Wan2.1 T2V 1.3B model using
 ### 0. Make sure you have installed VSA
 
 ```bash
-pip install vsa
+uv pip install vsa
 ```
 
 ### 1. Download dataset:

examples/distill/Wan2.2-TI2V-5B-Diffusers/Data-free/README.md

@@ -4,7 +4,7 @@ These are end-to-end example scripts for distilling Wan2.2 TI2V 5B model DMD+VSA
 ### 0. Make sure you have installed VSA
 
 ```bash
-pip install vsa
+uv pip install vsa
 ```
 
 ### Data-free Distillation

examples/distill/Wan2.2-TI2V-5B-Diffusers/crush_smol/README.md

@@ -4,7 +4,7 @@ These are end-to-end example scripts for distilling Wan2.2 TI2V 5B model DMD+VSA
 ### 0. Make sure you have installed VSA
 
 ```bash
-pip install vsa
+uv pip install vsa
 ```
 
 ### 1. Download dataset:

examples/inference/basic/README.md

@@ -28,6 +28,11 @@ For an example running DMD+VSA inference:
 python examples/inference/basic/basic_dmd.py
 ```
 
+For the typed config/request path added during the inference API refactor:
+```
+python examples/inference/basic/basic_dmd_new_api.py
+```
+
 ## Basic Walkthrough
 
 All you need to generate videos using multi-gpus from state-of-the-art diffusion pipelines is the following few lines!

examples/inference/basic/basic.py

@@ -1,6 +1,6 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.configs.sample import SamplingParam
+# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples"
 def main():

examples/inference/basic/basic_cosmos2_5_i2w.py

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
+from fastvideo.api.sampling_param import SamplingParam
 
 
 def main():

examples/inference/basic/basic_cosmos2_5_t2w.py

@@ -1,5 +1,5 @@
 from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
+from fastvideo.api.sampling_param import SamplingParam
 
 
 def main():

examples/inference/basic/basic_cosmos2_5_v2w.py

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
+from fastvideo.api.sampling_param import SamplingParam
 
 
 def main():

examples/inference/basic/basic_dmd.py

@@ -2,7 +2,7 @@ import os
 import time
 from fastvideo import VideoGenerator
 
-from fastvideo.configs.sample import SamplingParam
+from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_dmd2"
 def main():

examples/inference/basic/basic_dmd_new_api.py

@@ -0,0 +1,98 @@
+import os
+import time
+
+from fastvideo import VideoGenerator
+from fastvideo.api import (
+    EngineConfig,
+    GenerationRequest,
+    GeneratorConfig,
+    OffloadConfig,
+    OutputConfig,
+    PipelineSelection,
+)
+
+OUTPUT_PATH = "video_samples_dmd2_typed"
+
+
+def main():
+    os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "VIDEO_SPARSE_ATTN"
+
+    model_name = "FastVideo/FastWan2.1-T2V-1.3B-Diffusers"
+    generator_config = GeneratorConfig(
+        model_path=model_name,
+        engine=EngineConfig(
+            num_gpus=1,
+            use_fsdp_inference=False,
+            offload=OffloadConfig(
+                text_encoder=True,
+                pin_cpu_memory=True,
+                dit=False,
+                vae=False,
+            ),
+        ),
+        # PR 2 still routes a few advanced inference knobs through the
+        # compatibility bridge until they get first-class typed fields.
+        pipeline=PipelineSelection(
+            experimental={
+                "VSA_sparsity": 0.8,
+            },
+        ),
+    )
+
+    load_start_time = time.perf_counter()
+    generator = VideoGenerator.from_config(generator_config)
+    load_end_time = time.perf_counter()
+    load_time = load_end_time - load_start_time
+
+    prompt = (
+        "A neon-lit alley in futuristic Tokyo during a heavy rainstorm at night. "
+        "The puddles reflect glowing signs in kanji, advertising ramen, karaoke, "
+        "and VR arcades. A woman in a translucent raincoat walks briskly with an "
+        "LED umbrella. Steam rises from a street food cart, and a cat darts "
+        "across the screen. Raindrops are visible on the camera lens, creating "
+        "a cinematic bokeh effect."
+    )
+    request = GenerationRequest(
+        prompt=prompt,
+        output=OutputConfig(
+            output_path=OUTPUT_PATH,
+            save_video=True,
+            return_frames=False,
+        ),
+    )
+
+    start_time = time.perf_counter()
+    result = generator.generate(request)
+    end_time = time.perf_counter()
+    gen_time = end_time - start_time
+
+    prompt2 = (
+        "A majestic lion strides across the golden savanna, its powerful frame "
+        "glistening under the warm afternoon sun. The tall grass ripples gently "
+        "in the breeze, enhancing the lion's commanding presence. The tone is "
+        "vibrant, embodying the raw energy of the wild. Low angle, steady "
+        "tracking shot, cinematic."
+    )
+    request2 = GenerationRequest(
+        prompt=prompt2,
+        output=OutputConfig(
+            output_path=OUTPUT_PATH,
+            save_video=True,
+            return_frames=False,
+        ),
+    )
+
+    start_time = time.perf_counter()
+    result2 = generator.generate(request2)
+    end_time = time.perf_counter()
+    gen_time2 = end_time - start_time
+
+    print(f"Time taken to load model: {load_time} seconds")
+    print(f"Time taken to generate video: {gen_time} seconds")
+    print(f"First output written to: {result.video_path}")
+    print(f"Time taken to generate video2: {gen_time2} seconds")
+    print(f"Second output written to: {result2.video_path}")
+
+
+if __name__ == "__main__":
+    main()

examples/inference/basic/basic_gen3c.py

@@ -0,0 +1,109 @@
+"""
+GEN3C: 3D-aware camera-controlled video generation.
+
+This example generates a video from a single input image with camera control.
+The pipeline uses MoGe depth estimation, 3D point cloud forward warping,
+and the GEN3C diffusion model.
+
+Requirements:
+  1. Install MoGe:
+     uv pip install git+https://github.com/microsoft/MoGe.git
+     If you hit `ImportError: libGL.so.1`, install:
+     sudo apt-get update && sudo apt-get install -y libgl1 libglib2.0-0 libsm6 libxext6 libxrender1
+  2. Download and convert weights:
+     huggingface-cli download nvidia/GEN3C-Cosmos-7B --local-dir official_weights/GEN3C-Cosmos-7B
+     python scripts/checkpoint_conversion/convert_gen3c_to_fastvideo.py \
+       --source ./official_weights/GEN3C-Cosmos-7B/model.pt \
+       --output ./converted_weights/GEN3C-Cosmos-7B \
+       --components-source nvidia/Cosmos-Predict2-2B-Video2World
+  3. Provide an input image for 3D-conditioned generation.
+"""
+
+import argparse
+
+from fastvideo import VideoGenerator
+
+
+def main():
+    parser = argparse.ArgumentParser(description="GEN3C video generation")
+    parser.add_argument("--model_path",
+                        type=str,
+                        default="converted_weights/GEN3C-Cosmos-7B")
+    parser.add_argument("--image_path",
+                        type=str,
+                        default=None,
+                        help="Input image for 3D cache conditioning")
+    parser.add_argument("--prompt",
+                        type=str,
+                        default="A slow camera pan over a sunlit landscape.")
+    parser.add_argument(
+        "--negative_prompt",
+        type=str,
+        default=(
+            "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, "
+            "over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, "
+            "underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, "
+            "jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special "
+            "effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and "
+            "flickering. Overall, the video is of poor quality."
+        ),
+    )
+    parser.add_argument("--trajectory",
+                        type=str,
+                        default="left",
+                        choices=[
+                            "left", "right", "up", "down", "zoom_in",
+                            "zoom_out", "clockwise", "counterclockwise", "none"
+                        ])
+    parser.add_argument("--movement_distance", type=float, default=0.3)
+    parser.add_argument("--camera_rotation",
+                        type=str,
+                        default="center_facing",
+                        choices=[
+                            "center_facing", "no_rotation",
+                            "trajectory_aligned"
+                        ])
+    parser.add_argument("--height", type=int, default=704)
+    parser.add_argument("--width", type=int, default=1280)
+    parser.add_argument("--num_frames", type=int, default=121)
+    parser.add_argument("--num_inference_steps", type=int, default=35)
+    parser.add_argument("--guidance_scale", type=float, default=1.0)
+    parser.add_argument("--output_path",
+                        type=str,
+                        default="outputs_video/gen3c.mp4")
+    parser.add_argument("--seed", type=int, default=42)
+    args = parser.parse_args()
+
+    generator = VideoGenerator.from_pretrained(
+        args.model_path,
+        num_gpus=1,
+        use_fsdp_inference=False,
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=True,
+    )
+
+    video = generator.generate_video(
+        args.prompt,
+        negative_prompt=args.negative_prompt,
+        image_path=args.image_path,
+        trajectory_type=args.trajectory,
+        movement_distance=args.movement_distance,
+        camera_rotation=args.camera_rotation,
+        height=args.height,
+        width=args.width,
+        num_frames=args.num_frames,
+        num_inference_steps=args.num_inference_steps,
+        guidance_scale=args.guidance_scale,
+        fps=24,
+        seed=args.seed,
+        output_path=args.output_path,
+        save_video=True,
+    )
+
+    generator.shutdown()
+
+
+if __name__ == "__main__":
+    main()

examples/inference/basic/basic_hy15.py

@@ -1,6 +1,6 @@
 from fastvideo import VideoGenerator
 import json
-# from fastvideo.configs.sample import SamplingParam
+# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_hy15"
 def main():

examples/inference/basic/basic_hy15_1080p.py

@@ -1,6 +1,6 @@
 from fastvideo import VideoGenerator
 import json
-# from fastvideo.configs.sample import SamplingParam
+# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_hy15_1080p"
 def main():

examples/inference/basic/basic_lingbotworld_base_cam.py

@@ -1,7 +1,7 @@
 from fastvideo import VideoGenerator
 from fastvideo.models.dits.lingbotworld.cam_utils import prepare_camera_embedding
 
-# from fastvideo.configs.sample import SamplingParam
+# from fastvideo.api.sampling_param import SamplingParam
 OUTPUT_PATH = "video_samples_lingbotworld"
 def main():
     # FastVideo will automatically use the optimal default arguments for the