Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 SolitaryThinkerandClaude Opus 4.6
|
4bcaf9bef8 |
@@ -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
|
||||
|
||||
@@ -1,96 +0,0 @@
|
||||
#!/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"
|
||||
@@ -1,333 +0,0 @@
|
||||
---
|
||||
name: decompose-pipeline-pr
|
||||
description: Decompose an oversized FastVideo pipeline PR into a stack of independently-reviewable PRs. Tiers the diff by blast radius (invisible / dead code / cross-cutting infra / activation), produces a branch graph and worktree bootstrap, drafts the AGENTS.md manifest, flags missing tests on cross-cutting infra changes, and extracts lessons from the PR body.
|
||||
---
|
||||
|
||||
# Decompose Pipeline PR
|
||||
|
||||
## Purpose
|
||||
|
||||
When a PR adds a new pipeline (or first-class component port) and crosses
|
||||
~3,000 LOC, single-shot review converges to rubber-stamping. This skill
|
||||
decomposes such a PR into a stack of independently-reviewable PRs without
|
||||
disturbing `main`.
|
||||
|
||||
It is the inverse of `add-model`: where `add-model` walks adding a new
|
||||
pipeline as a fresh PR, this skill walks decomposing an existing oversized
|
||||
pipeline PR.
|
||||
|
||||
**Worked example:** PR #1280 (daVinci-MagiHuman, 9,812 LOC, 56 files) →
|
||||
2 prerequisite PRs off main + 8-PR stack:
|
||||
- #1293 `will/activation-trace` (prerequisite)
|
||||
- #1294 `will/loader-infra` (prerequisite)
|
||||
- #1295 (1/8) housekeeping
|
||||
- #1296 (2/8) t5gemma encoder
|
||||
- #1297 (3/8) DiT
|
||||
- #1298 (4/8) pipeline stages
|
||||
- #1299 (5/8) pipeline orchestrator
|
||||
- #1300 (6/8) provenance (AGENTS.md, JOURNAL.md, lessons)
|
||||
- #1301 (7/8) conversion scripts
|
||||
- #1302 (8/8) registry activation
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Open PR number on `hao-ai-lab/FastVideo` (or any FastVideo fork)
|
||||
- `gh` CLI authenticated against the target remote
|
||||
- Local git worktree support (`git worktree`)
|
||||
- Git config `user.name` / `user.email` set
|
||||
- Pre-commit installed (`pre-commit install --hook-type pre-commit --hook-type commit-msg`)
|
||||
- The target PR's branch fetched locally as `origin/<feature-branch>`
|
||||
|
||||
## Inputs
|
||||
|
||||
| Parameter | Required | Description |
|
||||
|-----------|----------|-------------|
|
||||
| PR number or URL | Yes | E.g. `1280` or `https://github.com/hao-ai-lab/FastVideo/pull/1280` |
|
||||
| Max desired PR size | No | Defaults to ~2,500 LOC of code per stack PR (excluding generated/journal files) |
|
||||
| Output dir | No | Defaults to `.agents/exploration/decompose-<pr-number>.md` |
|
||||
|
||||
## Steps
|
||||
|
||||
### 1. Verify ground truth (do not trust `gh pr diff --name-only`)
|
||||
|
||||
`gh pr diff <N> --name-only` has been observed to emit phantom file entries.
|
||||
Always cross-check against the authoritative `git diff`:
|
||||
|
||||
```bash
|
||||
git fetch origin pull/<N>/head:<feature-branch>
|
||||
git diff origin/main..origin/<feature-branch> --name-status > /tmp/pr-<N>-files.txt
|
||||
git diff origin/main..origin/<feature-branch> --stat
|
||||
```
|
||||
|
||||
Use the `--name-status` output as the authoritative file list. If it
|
||||
disagrees with `gh pr diff --name-only`, trust the git diff.
|
||||
|
||||
### 2. Tier the diff by blast radius
|
||||
|
||||
Classify every changed file into one of four tiers:
|
||||
|
||||
| Tier | Description | Examples |
|
||||
|---|---|---|
|
||||
| **Tier 0 — Invisible** | Lint/style/CI configs that don't affect runtime | `.gitignore`, `pyproject.toml` (codespell only), `.agents/skills/index.jsonl` stubs |
|
||||
| **Tier 1 — Dead code** | New files in their own dirs; aggregator one-liners | `fastvideo/models/dits/<new>/`, `fastvideo/pipelines/basic/<new>/`, `examples/inference/basic/basic_<new>*.py`, `tests/local_tests/<new>/`, `__init__.py` exports |
|
||||
| **Tier 2 — Cross-cutting infra** | Modifications to files used by every pipeline | See protected-paths list below |
|
||||
| **Tier 3 — Activation switch** | `register_configs(...)` calls + the example scripts that demo them | `fastvideo/registry.py` |
|
||||
|
||||
**FastVideo Tier 2 protected paths:**
|
||||
```
|
||||
fastvideo/utils.py
|
||||
fastvideo/pipelines/composed_pipeline_base.py
|
||||
fastvideo/models/loader/component_loader.py
|
||||
fastvideo/configs/models/dits/__init__.py
|
||||
fastvideo/configs/models/encoders/__init__.py
|
||||
fastvideo/configs/models/vaes/__init__.py
|
||||
fastvideo/envs.py
|
||||
fastvideo/fastvideo_args.py
|
||||
fastvideo/distributed/**
|
||||
fastvideo/layers/**
|
||||
fastvideo/attention/**
|
||||
fastvideo/registry.py # treat as Tier 3 if change is the activation
|
||||
```
|
||||
|
||||
Tier 3 detection (mechanical):
|
||||
```bash
|
||||
git diff origin/main..origin/<feature-branch> -- fastvideo/registry.py | \
|
||||
grep -E "^\+.*register_configs\("
|
||||
```
|
||||
|
||||
If `registry.py` only contains `register_configs` additions, treat it as
|
||||
Tier 3. If it modifies existing behavior, treat it as Tier 2 (rare).
|
||||
|
||||
### 3. Identify reusable Tier-1 components
|
||||
|
||||
Within Tier 1, look for sub-trees that are **not** model-specific and could
|
||||
land separately:
|
||||
|
||||
- Encoders matching a known multi-model base (T5/T5-Gemma/Llama/Gemma/CLIP variants)
|
||||
- New stage classes that subclass shared bases without referencing the new model
|
||||
- Hook/profiler/debug infra under `fastvideo/hooks/`
|
||||
- New helpers that have no model-specific dependencies
|
||||
|
||||
These get split into their own PRs (e.g. PR 4 `t5gemma-encoder` in the
|
||||
MagiHuman example).
|
||||
|
||||
### 4. Hunt for missing test coverage on Tier 2 changes
|
||||
|
||||
For every Tier-2 file modified, check whether the original PR added unit
|
||||
tests for the new behavior:
|
||||
|
||||
```bash
|
||||
for f in <list-of-tier-2-files>; do
|
||||
echo "=== Tests for $f ==="
|
||||
git diff origin/main..origin/<feature-branch> -- \
|
||||
"$(echo $f | sed 's|fastvideo/|fastvideo/tests/|; s|\.py|*|')"
|
||||
done
|
||||
```
|
||||
|
||||
If a Tier-2 PR has no accompanying tests, **emit a "must-add tests" list**
|
||||
with a sketch of the case grid. Tier-2 PRs do not ship without those tests.
|
||||
|
||||
The MagiHuman example required this for PR-B (`utils.py`): the original PR
|
||||
shipped no `test_utils_loader.py`, so the decomposition added 9 unit-test
|
||||
cases covering the umbrella-detector boundary, the optional-component-dirs
|
||||
relaxation, and regression coverage on every existing 2-segment HF id.
|
||||
|
||||
### 5. Build the dependency DAG and topo-sort
|
||||
|
||||
Edges:
|
||||
- Tier 2 infra → Tier 1 code that imports it
|
||||
- Reusable Tier 1 components → model-specific Tier 1 code that uses them
|
||||
(encoder before DiT before pipeline)
|
||||
- Tier 1 → Tier 3 (activation always last)
|
||||
- Tier 0 has no dependents (lands first as a freebie)
|
||||
|
||||
Topo-sort produces the stack ordering. Pull Tier-2 PRs **out of the stack**
|
||||
when they have no model-specific dependency — they should land off main
|
||||
with their own focused review, not buried in a model port.
|
||||
|
||||
Render as a tree (markdown):
|
||||
|
||||
```
|
||||
main
|
||||
├─ <prereq-A>
|
||||
│ └─ <prereq-B>
|
||||
│ ├─ <stack-01-housekeeping>
|
||||
│ │ └─ <stack-02-encoder>
|
||||
│ │ └─ <stack-03-dit>
|
||||
│ │ └─ ...
|
||||
│ │ └─ <stack-N-activate>
|
||||
│ └─ (parallel) <skill-pr> off main
|
||||
```
|
||||
|
||||
### 6. Detect mis-shelved docs and debug scratch
|
||||
|
||||
Two categories to flag:
|
||||
|
||||
- **Mis-shelved docs**: Markdown files under `tests/local_tests/` are
|
||||
journals, not tests. Flag for relocation to the package dir as
|
||||
`JOURNAL.md`.
|
||||
- **Debug scratch**: files starting with `_debug_`, `_scratch_`, or
|
||||
`_explore_`. Flag for drop (do not carry into any output PR).
|
||||
|
||||
For MagiHuman: `tests/local_tests/magi-human.md` → relocate. Two
|
||||
`_debug_magi_human_*.py` files → drop.
|
||||
|
||||
### 7. Author the AGENTS.md manifest skeleton
|
||||
|
||||
For the new pipeline package, generate a 6-section `AGENTS.md` scaffold
|
||||
with the file table pre-populated from the diff:
|
||||
|
||||
1. **Manifest** — file table by role
|
||||
2. **Parity invariants** — load-bearing rules with one-paragraph each + lesson refs
|
||||
3. **Cross-refs** — "If you change X, re-run Y" matrix
|
||||
4. **Run book** — single pytest command + prereqs (HF tokens, GPU, wall-time)
|
||||
5. **Open questions** — known issues (e.g. tolerance carve-outs)
|
||||
6. **Provenance** — PR table with branch names and source SHA
|
||||
|
||||
The provenance section is filled incrementally during stack execution and
|
||||
finalized in the activation PR.
|
||||
|
||||
### 8. Extract lessons from the PR body
|
||||
|
||||
Scan the PR body for sections titled "Key implementation work", "Bug hunt",
|
||||
"Lessons", or sentences with patterns like "took N waves to localize",
|
||||
"silent regression", "investigation revealed". Each becomes a candidate
|
||||
`.agents/lessons/<YYYY-MM-DD>_<slug>.md` draft.
|
||||
|
||||
Lessons MUST follow the existing template in
|
||||
`.agents/lessons/README.md`:
|
||||
- YAML frontmatter: `date`, `experiment`, `category`, `severity`
|
||||
- Sections: What Happened, Root Cause, Fix / Workaround, Prevention
|
||||
- Filename: `<YYYY-MM-DD>_<short-slug>.md`
|
||||
|
||||
Lessons co-locate with the code they concern: a conversion-script lesson
|
||||
lands in the same PR as the conversion script, not in the docs PR.
|
||||
|
||||
### 9. Emit the commit-footer convention
|
||||
|
||||
Every commit in the stack ends with:
|
||||
|
||||
```
|
||||
<Feature>-Stack: N/M
|
||||
```
|
||||
|
||||
E.g. `Magi-Stack: 5/8`. Use the package directory name as the feature key.
|
||||
After all PRs squash-merge, `git log --grep='^<Feature>-Stack:'` reconstructs
|
||||
the lineage even if PR numbers later get renumbered.
|
||||
|
||||
### 10. Produce the worktree bootstrap
|
||||
|
||||
Generate a runnable bash script:
|
||||
|
||||
```bash
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
REPO=/home/<user>/FastVideo
|
||||
WORKTREE=/home/<user>/FastVideoMagi # NB: directory name must be a valid
|
||||
# Python identifier (no hyphens) so
|
||||
# mypy doesn't choke
|
||||
SOURCE_PR=<N>
|
||||
SOURCE_BRANCH=will/<feature>
|
||||
SOURCE_SHA=$(git -C "$REPO" rev-parse "origin/$SOURCE_BRANCH")
|
||||
|
||||
git -C "$REPO" fetch origin main:main
|
||||
git -C "$REPO" fetch "origin/$SOURCE_BRANCH"
|
||||
git -C "$REPO" worktree add "$WORKTREE" origin/main
|
||||
|
||||
# Capture baseline for provenance
|
||||
mkdir -p "$REPO/.agents/exploration"
|
||||
cat > "$REPO/.agents/exploration/<feature>-baseline-${SOURCE_SHA:0:8}.txt" <<EOF
|
||||
Source PR: <repo>#$SOURCE_PR
|
||||
Source SHA: $SOURCE_SHA
|
||||
Authoritative file count: $(git -C "$REPO" diff origin/main..origin/$SOURCE_BRANCH --name-only | wc -l)
|
||||
Date captured: $(date -u +%Y-%m-%dT%H:%M:%SZ)
|
||||
EOF
|
||||
```
|
||||
|
||||
### 11. Author preserve via `git checkout`, not `cherry-pick`
|
||||
|
||||
For each stack PR:
|
||||
|
||||
```bash
|
||||
git -C "$WORKTREE" switch -c <new-branch> <base-branch>
|
||||
git -C "$WORKTREE" checkout origin/<source-branch> -- <file1> <file2> ...
|
||||
git -C "$WORKTREE" commit -m "[<scope>]: <subject>
|
||||
|
||||
<body>
|
||||
|
||||
<Feature>-Stack: N/M"
|
||||
git -C "$WORKTREE" push -u origin <new-branch>
|
||||
gh pr create --base <base-branch> --head <new-branch> --title "..." --body "$(cat <<EOF ... EOF)"
|
||||
```
|
||||
|
||||
Notes:
|
||||
- `git checkout origin/<source> -- <files>` extracts only the named files,
|
||||
preserving the diff. The original PR's author is **not** preserved on the
|
||||
new commit (it's authored by whoever runs the script). Reference the
|
||||
original PR + source SHA in every commit body and PR description for
|
||||
authorship attribution.
|
||||
- **Never use `git cherry-pick`** for this workflow — cherry-pick applies
|
||||
whole commits, which mixes concerns across PR boundaries.
|
||||
|
||||
## Outputs
|
||||
|
||||
The skill produces:
|
||||
|
||||
1. A markdown decomposition plan (`.agents/exploration/decompose-<pr>.md`)
|
||||
2. A proposed branch graph
|
||||
3. A worktree-bootstrap script
|
||||
4. Per-PR file allocation lists (under `/tmp/<feature>-stack/`)
|
||||
5. AGENTS.md scaffolds for any new pipeline packages
|
||||
6. Draft lesson files (placed alongside the PR that owns the code they concern)
|
||||
7. A finalized provenance table for the package AGENTS.md
|
||||
|
||||
## Anti-Patterns
|
||||
|
||||
The skill should warn against:
|
||||
|
||||
- **"Just rebase the megaPR into smaller commits."** Doesn't help review;
|
||||
reviewer still sees one PR.
|
||||
- **Co-locating tests under the new package.** FastVideo's convention is
|
||||
by-kind under `fastvideo/tests/` and `tests/local_tests/<family>/`. Don't
|
||||
invent a new layout per pipeline.
|
||||
- **Splitting Tier 2 changes into "one file per PR."** Tier 2 PRs are
|
||||
about semantic units (e.g., "loader umbrella + optional component dirs"
|
||||
together because they jointly define the new diffusers-format contract),
|
||||
not file-count.
|
||||
- **Landing the activation switch first** ("just register, the code can
|
||||
be empty"). The skill enforces activation-last so every intermediate
|
||||
state is dead code, not broken code.
|
||||
- **Trusting `gh pr diff --name-only`.** Cross-check against
|
||||
`git diff origin/main..origin/<feature-branch> --name-status` —
|
||||
`gh`'s output has been observed to include phantom entries.
|
||||
- **Worktree dir names with hyphens.** mypy interprets them as invalid
|
||||
Python package names and refuses to run. Use CamelCase or underscores.
|
||||
- **Skipping the lesson-extraction step.** PR bodies contain the most
|
||||
expensive learnings of the original implementation. Losing them to a
|
||||
squash-merge is the silent decay of institutional knowledge.
|
||||
|
||||
## Example Usage
|
||||
|
||||
```
|
||||
User: split PR 1280
|
||||
Agent: [invokes decompose-pipeline-pr]
|
||||
→ produces .agents/exploration/decompose-1280.md with:
|
||||
- tiered file table (56 files: 3 tier-0, 35 tier-1, 9 tier-2,
|
||||
9 tier-3)
|
||||
- branch graph (PR-A + PR-B + 8-PR stack)
|
||||
- worktree bootstrap script
|
||||
- per-PR file lists
|
||||
- AGENTS.md scaffold for fastvideo/pipelines/basic/magi_human/
|
||||
- 3 draft lessons extracted from the PR body
|
||||
→ asks user to confirm before opening branches
|
||||
```
|
||||
|
||||
## References
|
||||
|
||||
- The MagiHuman decomposition (worked example):
|
||||
`fastvideo/pipelines/basic/magi_human/AGENTS.md` (after PR #1302 merges)
|
||||
- Existing skill: `.agents/skills/add-model/SKILL.md` (the inverse — adding
|
||||
a new pipeline as a fresh PR)
|
||||
- Lesson template: `.agents/lessons/README.md`
|
||||
- Skill template: `.agents/skills/SKILL_TEMPLATE.md`
|
||||
@@ -5,7 +5,3 @@
|
||||
{"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": "decompose-pipeline-pr", "description": "Decompose an oversized FastVideo pipeline PR into a stack of independently-reviewable PRs. Tiers the diff by blast radius (invisible / dead code / cross-cutting infra / activation), produces a branch graph and worktree bootstrap, drafts the AGENTS.md manifest, flags missing tests on cross-cutting infra changes, and extracts lessons from the PR body. Worked example: PR #1280 daVinci-MagiHuman (9.8k LOC) decomposed into 10 stacked PRs.", "path": "decompose-pipeline-pr/SKILL.md", "status": "tested", "trust": "medium"}
|
||||
{"name": "reseed-performance-baseline", "description": "Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, or environment-caused benchmark shift. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed for an accepted reason and the rolling median baseline must be advanced by replicating one reviewed shifted source result into three success=true records, or five records when explicitly requested", "path": "reseed-performance-baseline/SKILL.md", "status": "draft", "trust": "low"}
|
||||
|
||||
@@ -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).
|
||||
|
||||
@@ -1,476 +0,0 @@
|
||||
---
|
||||
name: reseed-performance-baseline
|
||||
description: Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, or environment-caused benchmark shift using one or more reviewed normalized performance JSONs. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed for an accepted reason and the rolling median baseline in FastVideo/performance-tracking must be advanced from a consistent batch of reviewed source results. The workflow backs up existing history under /tmp, validates all source JSONs for the same (model_id, gpu_type), rejects internally inconsistent source batches, uploads one success=true reseed record per accepted source JSON, and offers to clean local temp state after a successful upload.
|
||||
---
|
||||
|
||||
# Re-seed Performance Baseline
|
||||
|
||||
## Purpose
|
||||
|
||||
Replace or advance the rolling performance baseline for a single
|
||||
`(model_id, gpu_type)` pair in the HF dataset
|
||||
`FastVideo/performance-tracking`.
|
||||
|
||||
Performance comparison uses the median of up to the last 5 successful records
|
||||
for the same model and GPU. Failed records are useful audit history, but they
|
||||
do not move the future baseline because `compare_baseline.py` loads records
|
||||
with `successful_only=True`.
|
||||
|
||||
This skill now reseeds from a reviewed batch of one or more source performance
|
||||
JSONs. It uploads one new `success=true` record per accepted source JSON; it
|
||||
does not blindly replicate one measurement into 3 or 5 records. The effective
|
||||
reseed size is therefore dynamic and equals the number of provided, validated,
|
||||
internally consistent source JSONs.
|
||||
|
||||
If the operator provides fewer than 3 records, call out that the last-5 rolling
|
||||
median may not move immediately. If the operator provides 3 consistent shifted
|
||||
records, the rolling median usually moves immediately. If the operator provides
|
||||
5 consistent shifted records, the last-5 window is effectively reset to the new
|
||||
runtime profile.
|
||||
|
||||
These records are intentional operator-approved baseline resets, not ordinary
|
||||
independent main-branch persistence. Mark them clearly with provenance fields
|
||||
so the HF history remains auditable.
|
||||
|
||||
Use this skill when a performance test fails for an intentional and reviewed
|
||||
reason, such as a torch/runtime/container upgrade that legitimately increases
|
||||
peak memory or changes timings. This is the performance equivalent of
|
||||
`reseed-ssim-references`: backup first, scope tightly, require explicit human
|
||||
approval, then upload reviewed accepted baseline records.
|
||||
|
||||
## When to use
|
||||
|
||||
- A PR or main run failed the rolling performance comparison by more than the
|
||||
allowed regression threshold, and maintainers agree the shift is caused by
|
||||
an intentional runtime, dependency, hardware image, or benchmark environment
|
||||
change rather than a FastVideo logic regression.
|
||||
- One or more shifted source result JSONs have been reviewed and accepted, and
|
||||
the operator wants to use those exact reviewed results to advance the rolling
|
||||
baseline.
|
||||
- The source batch is internally consistent: no provided source JSON regresses
|
||||
against the batch median by more than the configured tolerance.
|
||||
|
||||
## When not to use
|
||||
|
||||
- The benchmark failure might be a real code regression. Fix or investigate
|
||||
the code path first.
|
||||
- The fixed benchmark thresholds in
|
||||
`.buildkite/performance-benchmarks/tests/*.json` are too low. Those are a
|
||||
separate gate from the rolling HF baseline and may need a code review change.
|
||||
- There is no clear source run, commit, and rationale. Baseline history is a
|
||||
production signal; do not edit it without provenance.
|
||||
- The provided source JSONs disagree materially with each other. Rerun or
|
||||
investigate instead of uploading a noisy reseed batch.
|
||||
|
||||
## Inputs
|
||||
|
||||
| Parameter | Required | Description |
|
||||
|-----------|----------|-------------|
|
||||
| `model_id` | Yes | Benchmark id, e.g. `wan-t2v-1.3b-2gpu`. This maps to the HF subdirectory after `sanitize(model_id)`. |
|
||||
| `gpu_type` | Yes | Exact GPU device string from the performance record, e.g. the L40S device name emitted by CI. Baselines are GPU-specific. |
|
||||
| `source_results` | Yes | One or more local paths or Buildkite artifact URLs for accepted shifted performance JSONs. Prefer normalized `normalized_perf_*.json` artifacts emitted by `compare_baseline.py`. Accept `source_result` as an alias only for a single JSON. |
|
||||
| `max_intra_batch_regression` | No | Maximum allowed regression of any source JSON against the source batch median. Default: `PERF_MAX_REGRESSION` if set, otherwise `0.05` (5%). |
|
||||
| `intent_rationale` | Yes | One-line explanation for why the baseline shift is legitimate. This is written into provenance and should be reused in the PR. |
|
||||
|
||||
Hardcoded defaults:
|
||||
|
||||
- HF repo: `FastVideo/performance-tracking` (`HF_REPO_ID` override is
|
||||
supported by the code, but use the default unless the user explicitly asks).
|
||||
- Local sync root: `/tmp/perf-tracking` (`PERFORMANCE_TRACKING_ROOT` override
|
||||
is supported).
|
||||
- Backup root: `/tmp/performance_reseed_backup`.
|
||||
- Download scratch root for source artifact URLs: `/tmp/performance_reseed_source`.
|
||||
- Baseline window: last 5 `success=true` records for the same
|
||||
`(model_id, gpu_type)`.
|
||||
- Reseed count: dynamic. Upload exactly one accepted seed record per validated
|
||||
source JSON.
|
||||
|
||||
## Steps
|
||||
|
||||
### 1. Validate the target and source results
|
||||
|
||||
Normalize `source_results` to a list. If the user passes a single
|
||||
`source_result`, treat it as a one-element `source_results` list and report
|
||||
that a single record may not move the last-5 median immediately.
|
||||
|
||||
If any source result is a Buildkite artifact URL, download it first into a
|
||||
local scratch directory under `/tmp/performance_reseed_source/` and use the
|
||||
downloaded JSON path for the rest of the workflow. If the agent cannot access
|
||||
the artifact because Buildkite authentication is missing, ask the user to
|
||||
download the artifact manually and provide the local path.
|
||||
|
||||
Prefer the normalized Buildkite artifact emitted by `compare_baseline.py`:
|
||||
|
||||
```text
|
||||
perf_reports/results/normalized_perf_*.json
|
||||
```
|
||||
|
||||
That file is already in the HF tracking schema. Load each normalized JSON
|
||||
directly:
|
||||
|
||||
```python
|
||||
import json
|
||||
|
||||
with open(source_result, encoding="utf-8") as f:
|
||||
record = json.load(f)
|
||||
```
|
||||
|
||||
Stop if any normalized record's `model_id` or `gpu_type` does not match the
|
||||
requested `model_id` and `gpu_type`.
|
||||
|
||||
The source records may have `success: false` when they came from failed
|
||||
rolling baseline comparisons. That is expected; only the reviewed reseed
|
||||
records become new `success: true` baseline records after explicit approval.
|
||||
|
||||
Sort validated source records by their original `timestamp` ascending before
|
||||
preparing the seed records. If a source timestamp is missing or unparsable,
|
||||
preserve input order for those records and print a warning. This makes the
|
||||
fresh reseed timestamps deterministic and makes it clear which records enter
|
||||
the last-5 window when more than 5 source JSONs are provided.
|
||||
|
||||
Check that `HF_API_KEY` is exported. The sync path may be public, but the
|
||||
upload path requires write access.
|
||||
|
||||
### 1a. Check source batch consistency
|
||||
|
||||
Before syncing or preparing uploads, reject source batches that are internally
|
||||
inconsistent. Use the same metric direction as `compare_baseline.py`:
|
||||
|
||||
- Lower is better: `latency`, `memory`, `text_encoder_time_s`, `dit_time_s`,
|
||||
`vae_decode_time_s`.
|
||||
- Higher is better: `throughput`.
|
||||
|
||||
For each metric with at least two non-null source values:
|
||||
|
||||
1. Compute the source batch median.
|
||||
2. For lower-is-better metrics, compute `(source_value - batch_median) / batch_median`.
|
||||
3. For `throughput`, compute `(batch_median - source_value) / batch_median`.
|
||||
4. Stop if any source record regresses against the batch median by more than
|
||||
`max_intra_batch_regression`.
|
||||
|
||||
Default `max_intra_batch_regression` to `PERF_MAX_REGRESSION` when set,
|
||||
otherwise `0.05`. Print a table with per-source values, batch median, and
|
||||
worst intra-batch regression.
|
||||
|
||||
This check prevents uploading a mixed batch where one JSON is materially
|
||||
slower or faster than the others. If the batch fails this check, ask the user
|
||||
to provide a cleaner batch or explicitly investigate the variance. Do not
|
||||
silently drop outliers unless the user gives a concrete reviewed reason and a
|
||||
new source list.
|
||||
|
||||
### 1b. How to obtain source results from CI
|
||||
|
||||
The performance CI exports normalized source results for failed rolling
|
||||
baseline comparisons when `compare_baseline.py` ran. The preferred artifacts
|
||||
come from:
|
||||
|
||||
```text
|
||||
perf_reports/results/normalized_perf_*.json
|
||||
```
|
||||
|
||||
The normal operator flow is:
|
||||
|
||||
1. Open the failed Buildkite performance job or several reruns of the same
|
||||
benchmark after the accepted environment shift.
|
||||
2. Download the `normalized_perf_*.json` artifacts for the target benchmark.
|
||||
3. Pass all reviewed local paths or artifact URLs as `source_results`.
|
||||
|
||||
Do not scrape the Markdown performance summary to reconstruct JSON. The
|
||||
normalized JSON artifacts are the only supported source of truth for reseed
|
||||
metrics and provenance. Raw `fastvideo/tests/performance/results/perf_*.json`
|
||||
artifacts are not accepted by this skill. If no normalized JSON artifact is
|
||||
present, that run is not a valid source for baseline reseeding.
|
||||
|
||||
### 2. Sync and back up existing HF records under /tmp
|
||||
|
||||
Use `fastvideo/tests/performance/hf_store.py` helpers directly. Do **not** use
|
||||
`compare_baseline.py` as a sync shortcut; on full main runs it can persist
|
||||
records, while this step must only fetch and back up existing history.
|
||||
|
||||
The sync command pattern is:
|
||||
|
||||
```bash
|
||||
export PERFORMANCE_TRACKING_ROOT="${PERFORMANCE_TRACKING_ROOT:-/tmp/perf-tracking}"
|
||||
export HF_REPO_ID="${HF_REPO_ID:-FastVideo/performance-tracking}"
|
||||
PYTHONPATH=fastvideo/tests/performance python -c 'from hf_store import sync_from_hf; import os; sync_from_hf(os.environ["PERFORMANCE_TRACKING_ROOT"], strict=True)'
|
||||
```
|
||||
|
||||
Then back up only the sanitized model directory under `/tmp`:
|
||||
|
||||
```bash
|
||||
SHORT_COMMIT=$(git rev-parse --short=12 HEAD)
|
||||
TIMESTAMP=$(date -u +%Y%m%d_%H%M%S)
|
||||
MODEL_SAFE=$(PYTHONPATH=fastvideo/tests/performance python - <<'PY'
|
||||
from hf_store import sanitize
|
||||
print(sanitize("<model_id>"))
|
||||
PY
|
||||
)
|
||||
BACKUP_DIR="/tmp/performance_reseed_backup/${TIMESTAMP}_${SHORT_COMMIT}_${MODEL_SAFE}"
|
||||
mkdir -p "$BACKUP_DIR"
|
||||
cp -R "${PERFORMANCE_TRACKING_ROOT}/${MODEL_SAFE}" "$BACKUP_DIR/" 2>/dev/null || true
|
||||
```
|
||||
|
||||
Write provenance next to the backup:
|
||||
|
||||
```bash
|
||||
cat > "$BACKUP_DIR/PROVENANCE.txt" <<EOF
|
||||
model_id: <model_id>
|
||||
gpu_type: <gpu_type>
|
||||
source_results:
|
||||
- <source_result_1>
|
||||
- <source_result_2>
|
||||
reseed_record_count: <len(source_results)>
|
||||
max_intra_batch_regression: <threshold>
|
||||
head_commit: $(git rev-parse HEAD)
|
||||
timestamp_utc: $(date -u +%FT%TZ)
|
||||
reason: <intent_rationale>
|
||||
EOF
|
||||
```
|
||||
|
||||
If the backup has no prior records, this is not a destructive reseed; it is a
|
||||
first baseline seed. Continue, but report that baseline history was empty.
|
||||
|
||||
### 3. Compute old baseline and candidate shift
|
||||
|
||||
Load the last 5 successful records for the target:
|
||||
|
||||
```python
|
||||
from hf_store import load_records_for_model
|
||||
|
||||
records = load_records_for_model(
|
||||
"/tmp/perf-tracking",
|
||||
"<model_id>",
|
||||
"<gpu_type>",
|
||||
last_n=5,
|
||||
successful_only=True,
|
||||
)
|
||||
```
|
||||
|
||||
Print a small table showing old medians, source batch medians, candidate
|
||||
medians after appending the proposed seed records, and source batch spread for:
|
||||
|
||||
- `latency`
|
||||
- `throughput`
|
||||
- `memory`
|
||||
- `text_encoder_time_s`
|
||||
- `dit_time_s`
|
||||
- `vae_decode_time_s`
|
||||
|
||||
Also print how many successful old records exist. Make clear:
|
||||
|
||||
- 1 seed record usually does not move a last-5 median by itself.
|
||||
- 3 consistent seed records usually move the last-5 median immediately.
|
||||
- 5 consistent seed records effectively reset the last-5 window.
|
||||
- The records are intentional approved baseline resets and must be labeled
|
||||
that way.
|
||||
|
||||
### 4. Confirm intent
|
||||
|
||||
Require an explicit confirmation phrase before preparing the upload:
|
||||
|
||||
> About to RE-SEED performance baseline for `<model_id>` on `<gpu_type>`.
|
||||
> This will upload `<N>` new `success=true` records to
|
||||
> `FastVideo/performance-tracking/<sanitize(model_id)>/`, one per accepted
|
||||
> source JSON.
|
||||
>
|
||||
> Reason: `<intent_rationale>`
|
||||
> Source results: `<source_results>`
|
||||
> Reseed record count: `<N>`
|
||||
> Max intra-batch regression: `<threshold>`
|
||||
> Note: these records come from a reviewed source batch and are intended to
|
||||
> move the rolling median to the accepted runtime profile. They are not
|
||||
> ordinary main-branch persistence.
|
||||
> HEAD: `<git rev-parse --short=12 HEAD>`
|
||||
> Backup: `<BACKUP_DIR>`
|
||||
>
|
||||
> Reply `confirm performance reseed` to proceed, anything else to abort.
|
||||
|
||||
Do not continue unless the user types exactly `confirm performance reseed`.
|
||||
|
||||
### 5. Create the accepted seed records
|
||||
|
||||
Create one seed record from each normalized source result. Do not copy the
|
||||
source JSON wholesale.
|
||||
|
||||
Infer the baseline field allowlist from all existing HF records for the target
|
||||
`(model_id, gpu_type)` after syncing, including both `success=true` and
|
||||
`success=false` records. Use the union of non-provenance keys present in those
|
||||
target records, preserving only fields that also exist in the normalized
|
||||
source record or are explicitly set by the reseed workflow. Always include
|
||||
`model_id`, `timestamp`, and `success` because the upload path and baseline
|
||||
loader depend on them. Always set `timestamp` to a fresh reseed timestamp and
|
||||
`success` to `true`. Do not include unrelated source-only fields that are
|
||||
absent from existing HF records.
|
||||
|
||||
Exclude existing provenance or operator metadata from the inferred baseline
|
||||
field allowlist. At minimum, exclude keys prefixed with `baseline_reseed` and
|
||||
any fields known to be local-only audit metadata.
|
||||
|
||||
If there are no previous HF records for the target model/GPU, fall back to this
|
||||
default baseline field list:
|
||||
|
||||
- `model_id`
|
||||
- `timestamp`
|
||||
- `commit_sha`
|
||||
- `gpu_type`
|
||||
- `latency`
|
||||
- `throughput`
|
||||
- `memory`
|
||||
- `text_encoder_time_s`
|
||||
- `dit_time_s`
|
||||
- `vae_decode_time_s`
|
||||
- `success`
|
||||
|
||||
Do not upload extra fields from the source artifact.
|
||||
|
||||
Optional provenance fields are allowed and useful:
|
||||
|
||||
- `baseline_reseed: true`
|
||||
- `baseline_reseed_reason`
|
||||
- `baseline_reseed_source_result`
|
||||
- `baseline_reseed_source_timestamp`
|
||||
- `baseline_reseed_source_success`
|
||||
- `baseline_reseed_batch_size`
|
||||
- `baseline_reseed_batch_index`
|
||||
- `baseline_reseed_operator`
|
||||
- `baseline_reseed_max_intra_batch_regression`
|
||||
|
||||
Use a fresh reseed timestamp for each seed record, not the original source
|
||||
result timestamp. This is required because
|
||||
`load_records_for_model(..., last_n=5)` keeps the last records after loading
|
||||
the model directory; stale filenames/timestamps may not enter the last-5
|
||||
window and therefore may not move the median. Preserve the original source
|
||||
timestamp in `baseline_reseed_source_timestamp`.
|
||||
|
||||
Use the existing filename convention from `_write_tracking_record()`:
|
||||
`<sanitize(timestamp)>_<sanitize(commit_sha)>.json` under the sanitized model
|
||||
directory, but include a deterministic suffix such as `_reseed_01`,
|
||||
`_reseed_02`, and so on before `.json` so multiple records from the same
|
||||
batch do not overwrite each other.
|
||||
|
||||
If a source record already exists on HF with `success=false`, do not edit it
|
||||
in place unless the user explicitly asked for an audit-preserving correction.
|
||||
Prefer uploading new accepted seed records so failed history remains visible.
|
||||
|
||||
### 6. Pause before upload
|
||||
|
||||
Print:
|
||||
|
||||
- Backup directory path under `/tmp`.
|
||||
- Prepared local record paths under `PERFORMANCE_TRACKING_ROOT`.
|
||||
- HF paths that will receive the new records.
|
||||
- Old rolling medians.
|
||||
- Source batch medians, source batch spread, reseed count, and candidate
|
||||
medians.
|
||||
- Rationale.
|
||||
|
||||
Ask the user to reply exactly `upload`. Anything else aborts and leaves the
|
||||
prepared records plus backup on disk.
|
||||
|
||||
### 7. Upload only the scoped records
|
||||
|
||||
Use the shared storage helper so the path and repo type match CI:
|
||||
|
||||
```python
|
||||
from hf_store import upload_record
|
||||
|
||||
upload_record("<local_record_path>", record, strict=True)
|
||||
```
|
||||
|
||||
Run it once per prepared record. Each upload goes to:
|
||||
|
||||
```text
|
||||
FastVideo/performance-tracking/<sanitize(model_id)>/<record_filename>.json
|
||||
```
|
||||
|
||||
Never bulk upload the whole tracking root. Never modify another model's
|
||||
directory in the same operation.
|
||||
|
||||
### 8. Report outcome and offer cleanup
|
||||
|
||||
Report:
|
||||
|
||||
- Uploaded HF paths.
|
||||
- Backup directory under `/tmp`.
|
||||
- Local tracking root, usually `/tmp/perf-tracking`.
|
||||
- Old baseline window count and medians.
|
||||
- Source batch medians, source batch spread, reseed count, and candidate
|
||||
medians.
|
||||
- Expected effect based on reseed count.
|
||||
- Any separate threshold changes still needed in
|
||||
`.buildkite/performance-benchmarks/tests/*.json`.
|
||||
|
||||
Include the `intent_rationale` in the PR or follow-up comment so reviewers can
|
||||
distinguish an accepted baseline shift from a hidden regression.
|
||||
|
||||
After the upload is verified, ask whether the user wants to clear temporary
|
||||
local state. Explain what each directory is for:
|
||||
|
||||
- `PERFORMANCE_TRACKING_ROOT`, usually `/tmp/perf-tracking`: local synced
|
||||
mirror of `FastVideo/performance-tracking` plus the prepared local seed
|
||||
records used for scoped upload.
|
||||
- `/tmp/performance_reseed_backup/<...>`: local backup of the target model's
|
||||
pre-reseed HF history plus `PROVENANCE.txt`, kept so a bad reseed can be
|
||||
audited or corrected.
|
||||
- `/tmp/performance_reseed_source/<...>` when used: downloaded source JSON
|
||||
artifacts from Buildkite URLs.
|
||||
|
||||
Ask:
|
||||
|
||||
> Reseed succeeded. Do you want me to delete the local temp tracking mirror,
|
||||
> source downloads, and reseed backup under `/tmp`? These files are local
|
||||
> safety/audit artifacts only; HF already has the uploaded records.
|
||||
>
|
||||
> Reply `cleanup reseed temp` to delete them, anything else to keep them.
|
||||
|
||||
Do not delete anything unless the user replies exactly
|
||||
`cleanup reseed temp`. If cleanup is requested, remove only the specific
|
||||
directories created for this reseed. Never remove unrelated `/tmp` contents.
|
||||
|
||||
## Failure modes and handling
|
||||
|
||||
- **`HF_API_KEY` unset.** Stop before upload. Do not create an untracked
|
||||
process that appears to have reseeded but never reached HF.
|
||||
- **Source result does not match target.** Stop. The wrong benchmark or GPU
|
||||
would poison a separate baseline.
|
||||
- **Source batch is internally inconsistent.** Stop if any source regresses
|
||||
against the source batch median by more than `max_intra_batch_regression`.
|
||||
Ask for cleaner sources or a reviewed explanation before continuing.
|
||||
- **Too few source records to move the median.** Continue only after making
|
||||
clear that one or two records may not immediately move the last-5 median.
|
||||
- **The source results are noisy or suspicious.** Stop. Reseeding amplifies
|
||||
those measurements into the baseline, so they must be reviewed first.
|
||||
- **HF sync fails.** Stop for destructive reseeds. A stale or empty sync can
|
||||
make the old baseline look missing.
|
||||
- **Candidate still violates fixed thresholds.** Report that this skill only
|
||||
handles the rolling HF baseline; update benchmark JSON thresholds in code
|
||||
review if maintainers accept the new absolute limit.
|
||||
- **The user aborts at either confirmation.** Leave the backup and prepared
|
||||
records on disk. Nothing should be uploaded.
|
||||
- **The user declines cleanup.** Keep `/tmp/perf-tracking`, the source
|
||||
download directory if any, and `/tmp/performance_reseed_backup/<...>` in
|
||||
place for audit/debugging.
|
||||
- **A bad seed was uploaded.** Use the backup and HF history to identify the
|
||||
uploaded file, then remove or supersede it with an explicitly reviewed
|
||||
corrective record. Do not silently rewrite unrelated history.
|
||||
|
||||
## References
|
||||
|
||||
- `.agents/skills/reseed-ssim-references/SKILL.md` — safety pattern for
|
||||
intentional baseline replacement.
|
||||
- `fastvideo/tests/performance/compare_baseline.py` — normalization, rolling
|
||||
median comparison, and persistence rules.
|
||||
- `fastvideo/tests/performance/hf_store.py` — HF sync, record loading,
|
||||
`sanitize()`, and `upload_record()`.
|
||||
- `fastvideo/tests/performance/test_inference_performance.py` — source result
|
||||
JSON schema.
|
||||
- `.buildkite/performance-benchmarks/tests/*.json` — fixed absolute benchmark
|
||||
thresholds, separate from rolling baseline comparisons.
|
||||
|
||||
## Changelog
|
||||
|
||||
| Date | Change |
|
||||
|------|--------|
|
||||
| 2026-05-03 | Initial version. Sister workflow to `reseed-ssim-references`, scoped to one performance `(model_id, gpu_type)` baseline seed with backup, confirmation, provenance, and `success=true` upload. |
|
||||
| 2026-05-03 | Previous policy: replicate one approved shifted source result into 3 success records by default, or 5 only when explicitly requested. Add provenance marker for replicated-source reseeds. Superseded by the 2026-05-08 dynamic multi-source policy. |
|
||||
| 2026-05-08 | Replace fixed 3/5 replication with dynamic multi-source reseeding: upload one seed record per reviewed source JSON, validate intra-batch consistency, move backup/source scratch under `/tmp`, and ask whether to clean temp state after successful upload. |
|
||||
@@ -1,343 +0,0 @@
|
||||
---
|
||||
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. |
|
||||
@@ -1,376 +0,0 @@
|
||||
---
|
||||
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). |
|
||||
@@ -4,24 +4,21 @@ description: How to develop, validate, and register a new evaluation metric
|
||||
|
||||
# Evaluation Development SOP
|
||||
|
||||
Standard procedure for adding new video quality evaluation metrics to
|
||||
the FastVideo agent toolkit.
|
||||
Standard procedure for adding new video quality evaluation metrics to the
|
||||
FastVideo agent toolkit.
|
||||
|
||||
## When to use
|
||||
## When to Use
|
||||
|
||||
- You need a metric that does not exist in
|
||||
`.agents/memory/evaluation-registry/README.md`.
|
||||
- You need a metric that doesn't exist in `.agents/memory/evaluation-registry/README.md`.
|
||||
- An existing metric needs significant changes to its methodology.
|
||||
- You are exploring a new evaluation approach.
|
||||
- You're exploring a new evaluation approach.
|
||||
|
||||
## Steps
|
||||
|
||||
### 1. Research
|
||||
|
||||
- Search `.agents/memory/related-work/` for existing evaluation
|
||||
approaches.
|
||||
- Check `.agents/memory/evaluation-registry/README.md` for current
|
||||
metrics and their limitations.
|
||||
- Search `.agents/memory/related-work/` for existing evaluation approaches.
|
||||
- Check the `evaluation_registry.md` for current metrics and their limitations.
|
||||
- Review literature: FVD, CLIP-Score, human preference, etc.
|
||||
|
||||
### 2. Prototype
|
||||
@@ -32,25 +29,21 @@ the FastVideo agent toolkit.
|
||||
|
||||
### 3. Validate
|
||||
|
||||
- **Known-good test**: metric should score high on reference-quality
|
||||
videos.
|
||||
- **Known-bad test**: metric should score low on degraded or unrelated
|
||||
videos.
|
||||
- **Sensitivity test**: small quality differences should produce
|
||||
meaningful score differences.
|
||||
- **Known-good test**: Metric should score high on reference-quality videos.
|
||||
- **Known-bad test**: Metric should score low on degraded/unrelated videos.
|
||||
- **Sensitivity test**: Small quality differences should produce meaningful
|
||||
score differences.
|
||||
- Document thresholds and their justification.
|
||||
|
||||
### 4. Register
|
||||
|
||||
Update `.agents/memory/evaluation-registry/README.md`:
|
||||
|
||||
- Add the metric with status `Active`.
|
||||
- Document location, thresholds, and trust level.
|
||||
|
||||
### 5. Integrate
|
||||
|
||||
Update `.agents/skills/evaluate-video-quality/SKILL.md`:
|
||||
|
||||
Update `.agents/skills/evaluate-video-quality.md`:
|
||||
- Add the new metric as a section.
|
||||
- Include code examples and interpretation guide.
|
||||
|
||||
@@ -59,35 +52,3 @@ Update `.agents/skills/evaluate-video-quality/SKILL.md`:
|
||||
- Move the exploration log content into the skill.
|
||||
- Clean up the exploration file or mark it as `promoted`.
|
||||
- If anything went wrong during development, create a lesson.
|
||||
|
||||
## Where the metrics live
|
||||
|
||||
The eval suite is `fastvideo/eval/`. New metrics register themselves
|
||||
via `@register("<group>.<name>")` and are auto-discovered when
|
||||
`fastvideo.eval.metrics` is imported.
|
||||
|
||||
- **Native metrics** (SSIM, PSNR, LPIPS, optical flow, VLM): add a
|
||||
file under the appropriate group dir
|
||||
(`fastvideo/eval/metrics/common/`, `optical_flow/`, `videoscore2/`,
|
||||
`physics_iq/`).
|
||||
- **Metrics that wrap upstream research code**: follow the vbench
|
||||
pattern in `fastvideo/eval/metrics/vbench/`. The contract is:
|
||||
- Upstream lives as a git submodule under
|
||||
`fastvideo/third_party/eval/<bench>/`, pinned to a SHA in repo-root
|
||||
`.gitmodules`.
|
||||
- The metric package's `__init__.py` inserts the submodule path on
|
||||
`sys.path` and installs runtime compat shims (attribute-level
|
||||
monkey-patches) for any modern-dep drift. Do not modify upstream
|
||||
files on disk, and do not ship a `setup.sh`.
|
||||
- See `fastvideo/eval/README.md` for the worked vbench example.
|
||||
- Full porting guide:
|
||||
[`docs/contributing/eval-metrics.md`](../../docs/contributing/eval-metrics.md).
|
||||
|
||||
## Out of scope of the initial eval port
|
||||
|
||||
The following land in follow-up PRs:
|
||||
|
||||
- **MIND** metrics (depends on a separate `vipe` submodule).
|
||||
- **VBench-2.0** sibling package.
|
||||
- Native conversion of **FVD** under `fastvideo/eval/metrics/fvd/`.
|
||||
- The training-time `EvalCallback`.
|
||||
|
||||
@@ -29,17 +29,14 @@
|
||||
"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": 2,
|
||||
"num_measurement_runs": 5,
|
||||
"num_warmup_runs": 1,
|
||||
"num_measurement_runs": 3,
|
||||
"required_gpus": 2
|
||||
},
|
||||
"thresholds": {
|
||||
"L40S": {
|
||||
"max_generation_time_s": 34.0,
|
||||
"max_peak_memory_mb": 11000.0,
|
||||
"max_text_encoder_time_s": 5.0,
|
||||
"max_dit_time_s": 10.0,
|
||||
"max_vae_decode_time_s": 10.0
|
||||
"max_peak_memory_mb": 11000.0
|
||||
},
|
||||
"default": {
|
||||
"max_generation_time_s": 120.0,
|
||||
|
||||
@@ -15,21 +15,8 @@ log "Project root: $PROJECT_ROOT"
|
||||
# Install Modal if not available
|
||||
if ! python3 -m modal --version &> /dev/null; then
|
||||
log "Modal not found, installing..."
|
||||
if ! command -v uv &> /dev/null; then
|
||||
log "uv not found, bootstrapping..."
|
||||
if ! curl -LsSf https://astral.sh/uv/install.sh | sh; then
|
||||
log "Error: Failed to bootstrap uv via astral.sh installer."
|
||||
exit 1
|
||||
fi
|
||||
export PATH="$HOME/.local/bin:$PATH"
|
||||
if ! command -v uv &> /dev/null; then
|
||||
log "Error: uv still not on PATH after bootstrap."
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
# --break-system-packages preserves prior `pip install --user` semantics on PEP 668 agents.
|
||||
uv pip install --system --break-system-packages modal
|
||||
|
||||
python3 -m pip install modal
|
||||
|
||||
# Verify installation
|
||||
if ! python3 -m modal --version &> /dev/null; then
|
||||
log "Error: Failed to install modal. Please install it manually."
|
||||
@@ -76,86 +63,7 @@ EFFECTIVE_PR=${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
|
||||
}
|
||||
|
||||
_upload_normalized_perf_results() {
|
||||
local found=0
|
||||
while IFS= read -r -d '' target; do
|
||||
found=1
|
||||
log "Found normalized performance result: $target. Uploading to Buildkite..."
|
||||
buildkite-agent artifact upload "$target"
|
||||
done < <(find "$LOCAL_DIR" -path "*/results/normalized_perf_*.json" -print0)
|
||||
|
||||
if [ "$found" -eq 0 ]; then
|
||||
log "No normalized performance result artifacts found. This is expected when the rolling performance comparison did not run."
|
||||
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 "$LOCAL_DIR"
|
||||
}
|
||||
|
||||
# --- Main flow ---
|
||||
_download_reports || { _cleanup_local; return 1; }
|
||||
_upload_dashboard
|
||||
_upload_perf_summary
|
||||
_upload_normalized_perf_results
|
||||
_cleanup_modal_volume
|
||||
_cleanup_local
|
||||
}
|
||||
MODAL_ENV="BUILDKITE_REPO=$BUILDKITE_REPO BUILDKITE_COMMIT=$BUILDKITE_COMMIT BUILDKITE_PULL_REQUEST=$EFFECTIVE_PR IMAGE_VERSION=$IMAGE_VERSION"
|
||||
|
||||
case "$TEST_TYPE" in
|
||||
"encoder")
|
||||
@@ -216,9 +124,8 @@ case "$TEST_TYPE" in
|
||||
MODAL_COMMAND="$MODAL_ENV HF_API_KEY=$HF_API_KEY python3 -m modal run $MODAL_TEST_FILE::run_lora_extraction_tests"
|
||||
;;
|
||||
"performance")
|
||||
log "Running performance tests on Modal..."
|
||||
log "Running performance tests..."
|
||||
MODAL_COMMAND="$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..."
|
||||
@@ -240,10 +147,5 @@ 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
|
||||
|
||||
@@ -13,21 +13,8 @@ log "Project root: $PROJECT_ROOT"
|
||||
|
||||
if ! python3 -m pre_commit --version &> /dev/null; then
|
||||
log "pre-commit not found, installing..."
|
||||
if ! command -v uv &> /dev/null; then
|
||||
log "uv not found, bootstrapping..."
|
||||
if ! curl -LsSf https://astral.sh/uv/install.sh | sh; then
|
||||
log "Error: Failed to bootstrap uv via astral.sh installer."
|
||||
exit 1
|
||||
fi
|
||||
export PATH="$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
|
||||
|
||||
python3 -m pip install --user pre-commit==4.0.1
|
||||
|
||||
if ! python3 -m pre_commit --version &> /dev/null; then
|
||||
log "Error: Failed to install pre-commit."
|
||||
exit 1
|
||||
|
||||
@@ -2,8 +2,7 @@
|
||||
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 [infra] Add trace hooks
|
||||
[skill] Add agent skill
|
||||
[misc] Cleanup configs [new-model] Port Flux2
|
||||
|
||||
MERGE WORKFLOW:
|
||||
1. Ensure pre-commit passes and you have at least 1 approval
|
||||
|
||||
+5
-23
@@ -3,7 +3,7 @@ merge_protections:
|
||||
if:
|
||||
- base = main
|
||||
success_conditions:
|
||||
- "title~=(?i)^\\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model|skill|skills|infra)\\]"
|
||||
- "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
|
||||
@@ -79,22 +79,6 @@ pull_request_rules:
|
||||
label:
|
||||
add: ["type: new-model"]
|
||||
|
||||
- name: "label type: infra"
|
||||
conditions:
|
||||
- "title~=(?i)^\\[infra\\]"
|
||||
- -closed
|
||||
actions:
|
||||
label:
|
||||
add: ["type: infra"]
|
||||
|
||||
- name: "label type: skill"
|
||||
conditions:
|
||||
- "title~=(?i)^\\[skills?\\]"
|
||||
- -closed
|
||||
actions:
|
||||
label:
|
||||
add: ["type: skill"]
|
||||
|
||||
# ============================================================
|
||||
# Scope labels (from changed files)
|
||||
# ============================================================
|
||||
@@ -121,7 +105,7 @@ pull_request_rules:
|
||||
- files~=^fastvideo/pipelines/samplers/
|
||||
- files~=^fastvideo/entrypoints/
|
||||
- files~=^fastvideo/worker/
|
||||
- files~=^fastvideo/api/sampling_param
|
||||
- files~=^fastvideo/configs/sample/
|
||||
- files~=^fastvideo/configs/pipelines/
|
||||
- files~=^examples/inference/
|
||||
- -closed
|
||||
@@ -278,7 +262,7 @@ pull_request_rules:
|
||||
- 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|skill|skills|infra)\\]"
|
||||
- "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
|
||||
@@ -308,7 +292,7 @@ pull_request_rules:
|
||||
conditions:
|
||||
- -closed
|
||||
- -draft
|
||||
- "-title~=(?i)^\\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model|skill|skills|infra)\\]"
|
||||
- "-title~=(?i)^\\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model)\\]"
|
||||
actions:
|
||||
comment:
|
||||
message: |
|
||||
@@ -320,13 +304,11 @@ pull_request_rules:
|
||||
- `[refactor] Restructure training pipeline`
|
||||
- `[perf] Optimize attention kernel`
|
||||
- `[ci] Update test infrastructure`
|
||||
- `[infra] Add activation trace hooks`
|
||||
- `[docs] Add inference guide`
|
||||
- `[misc] Clean up configs`
|
||||
- `[new-model] Port Flux2 to FastVideo`
|
||||
- `[skill] Add add-model agent skill`
|
||||
|
||||
Valid tags: `feat`, `feature`, `bugfix`, `fix`, `refactor`, `perf`, `ci`, `infra`, `doc`, `docs`, `misc`, `chore`, `kernel`, `new-model`, `skill`, `skills`
|
||||
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.
|
||||
|
||||
|
||||
@@ -37,11 +37,10 @@ jobs:
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
|
||||
- name: Install dependencies
|
||||
run: uv pip install --system -r requirements-mkdocs.txt
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements-mkdocs.txt
|
||||
|
||||
- name: Setup Pages
|
||||
uses: actions/configure-pages@v4
|
||||
|
||||
@@ -56,11 +56,10 @@ jobs:
|
||||
with:
|
||||
python-version: '3.10'
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
|
||||
- name: Install build dependencies
|
||||
run: uv pip install --system build twine wheel
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install build twine wheel
|
||||
|
||||
- name: Build package
|
||||
run: |
|
||||
|
||||
@@ -131,13 +131,11 @@ 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: |
|
||||
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}}
|
||||
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}}
|
||||
nvcc --version
|
||||
python --version
|
||||
python -c "import torch; print('PyTorch:', torch.__version__)"
|
||||
@@ -147,20 +145,20 @@ jobs:
|
||||
- name: Build wheel
|
||||
run: |
|
||||
export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
|
||||
|
||||
uv pip install --system setuptools ninja packaging wheel triton scikit-build-core cmake build
|
||||
|
||||
|
||||
pip install 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="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
|
||||
|
||||
|
||||
# Build standard wheel (no local version suffix) for PyPI
|
||||
python -m build --wheel --outdir dist
|
||||
|
||||
|
||||
# Fix the wheel to be manylinux compliant
|
||||
uv pip install --system auditwheel
|
||||
pip install auditwheel
|
||||
# Point auditwheel at torch libs, but do not vendor them into the wheel.
|
||||
TORCH_LIB_DIR=$(python - <<'PY'
|
||||
import os
|
||||
@@ -213,13 +211,10 @@ jobs:
|
||||
pattern: 'fastvideo_kernel-py*'
|
||||
merge-multiple: true
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
|
||||
- name: Build source distribution
|
||||
run: |
|
||||
uv pip install --system build scikit-build-core cmake ninja
|
||||
|
||||
pip install 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
|
||||
|
||||
@@ -4,6 +4,3 @@
|
||||
[submodule "fastvideo-kernel/include/cutlass"]
|
||||
path = fastvideo-kernel/include/cutlass
|
||||
url = https://github.com/NVIDIA/cutlass.git
|
||||
[submodule "fastvideo/third_party/eval/vbench"]
|
||||
path = fastvideo/third_party/eval/vbench
|
||||
url = https://github.com/Vchitect/VBench.git
|
||||
|
||||
@@ -7,13 +7,20 @@ 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/.*|
|
||||
\.agents/.*|
|
||||
.github/workflows/publish-fastvideo.yml|
|
||||
.github/workflows/_template-build-image.yml
|
||||
.github/workflows/_template-build-image.yml|
|
||||
docs/source/inference/support_matrix.md
|
||||
)
|
||||
repos:
|
||||
- repo: https://github.com/google/yapf
|
||||
|
||||
@@ -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.
|
||||
@@ -23,8 +23,7 @@
|
||||
- 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`.
|
||||
- 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).
|
||||
- Target line length is 80.
|
||||
- Naming: `snake_case` for functions/files, `PascalCase` for classes, `UPPER_SNAKE_CASE` for constants.
|
||||
|
||||
## Testing Guidelines
|
||||
@@ -55,31 +54,3 @@ 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.
|
||||
|
||||
@@ -128,7 +128,7 @@ class CLIPFeatureExtractor(BaseFeatureExtractor):
|
||||
|
||||
def __init__(self, device: str = 'cuda', model_name: str = "openai/clip-vit-base-patch32"):
|
||||
if not TRANSFORMERS_AVAILABLE:
|
||||
raise ImportError("Please install transformers: uv pip install transformers")
|
||||
raise ImportError("Please install transformers: pip install transformers")
|
||||
super().__init__(device)
|
||||
self.processor = CLIPProcessor.from_pretrained(model_name)
|
||||
self.model = CLIPModel.from_pretrained(model_name).to(self.device)
|
||||
@@ -171,7 +171,7 @@ class VideoMAEFeatureExtractor(BaseFeatureExtractor):
|
||||
|
||||
def __init__(self, device: str = 'cuda', model_name: str = "MCG-NJU/videomae-base"):
|
||||
if not TRANSFORMERS_AVAILABLE:
|
||||
raise ImportError("Please install transformers: uv pip install transformers")
|
||||
raise ImportError("Please install transformers: pip install transformers")
|
||||
super().__init__(device)
|
||||
self.model = VideoMAEModel.from_pretrained(model_name).to(self.device)
|
||||
self.model.eval()
|
||||
|
||||
@@ -57,7 +57,7 @@ class I3DFeatureExtractor(nn.Module):
|
||||
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"uv pip install huggingface_hub") from e
|
||||
f"pip install huggingface_hub") from e
|
||||
|
||||
def preprocess(self, videos: torch.Tensor) -> torch.Tensor:
|
||||
"""
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
#!/bin/bash
|
||||
|
||||
# 1. Install missing dependency
|
||||
uv pip install -q opencv-python-headless transformers huggingface_hub
|
||||
pip install -q opencv-python-headless transformers huggingface_hub
|
||||
|
||||
# 2. Run FVD script
|
||||
python benchmarks/fvd/run_fvd.py
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
#!/bin/bash
|
||||
|
||||
# 1. Install missing dependency
|
||||
uv pip install -q opencv-python-headless
|
||||
pip install -q opencv-python-headless
|
||||
+2
-2
@@ -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 with `uv`.
|
||||
Currently, the only dependency is `fastvideo`, which can be installed using pip.
|
||||
|
||||
```bash
|
||||
uv pip install fastvideo
|
||||
pip install fastvideo
|
||||
```
|
||||
|
||||
#### Install missing custom nodes:
|
||||
|
||||
@@ -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/v0.9.4/flash_attn-2.8.3+cu128torch2.11-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/v0.7.16/flash_attn-2.8.3+cu128torch2.10-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
|
||||
|
||||
@@ -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/v0.9.4/flash_attn-2.8.3+cu128torch2.11-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/v0.7.16/flash_attn-2.8.3+cu128torch2.10-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
|
||||
|
||||
@@ -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/v0.9.4/flash_attn-2.8.3+cu128torch2.11-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/v0.7.16/flash_attn-2.8.3+cu128torch2.10-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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
+1
-1
@@ -6,7 +6,7 @@ This directory contains the FastVideo documentation built with MkDocs.
|
||||
|
||||
```bash
|
||||
# Install dependencies
|
||||
uv pip install -r requirements-mkdocs.txt
|
||||
pip install -r requirements-mkdocs.txt
|
||||
|
||||
# Serve docs with live reload (recommended for development)
|
||||
mkdocs serve
|
||||
|
||||
@@ -62,9 +62,9 @@ This page contains the complete API reference for the FastVideo library.
|
||||
show_root_toc_entry: true
|
||||
heading_level: 4
|
||||
|
||||
#### fastvideo.api.sampling_param
|
||||
#### fastvideo.configs.sample
|
||||
|
||||
::: fastvideo.api.sampling_param
|
||||
::: fastvideo.configs.sample
|
||||
options:
|
||||
show_source: true
|
||||
show_root_heading: true
|
||||
|
||||
@@ -1,210 +0,0 @@
|
||||
# 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. |
|
||||
@@ -173,7 +173,7 @@ Applied by Mergify based on which paths you modified. Multiple scope labels can
|
||||
| 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: inference` | `fastvideo/pipelines/basic/`, `fastvideo/pipelines/stages/`, `fastvideo/pipelines/samplers/`, `fastvideo/entrypoints/`, `fastvideo/worker/`, `fastvideo/configs/sample/`, `fastvideo/configs/pipelines/`, `examples/inference/` |
|
||||
| `scope: attention` | `fastvideo/attention/` |
|
||||
| `scope: kernel` | `fastvideo-kernel/`, `csrc/` |
|
||||
| `scope: data` | `fastvideo/dataset/`, `fastvideo/pipelines/preprocess/`, `examples/preprocessing/` |
|
||||
|
||||
@@ -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/api/sampling_param.py`: runtime sampling parameters.
|
||||
- `fastvideo/configs/sample/*`: default 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.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample 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)
|
||||
@@ -296,10 +296,8 @@ 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/` 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`.
|
||||
- See examples in `tests/local_tests/` (e.g., `tests/local_tests/upsamplers/`)
|
||||
and the commands 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`).
|
||||
@@ -321,8 +319,7 @@ Purpose:
|
||||
|
||||
- `fastvideo/configs/pipelines/` describes pipeline wiring and model module
|
||||
names.
|
||||
- `fastvideo/api/sampling_param.py` defines runtime sampling parameters.
|
||||
Defaults come from profiles in `fastvideo/pipelines/basic/<family>/profiles.py`.
|
||||
- `fastvideo/configs/sample/` defines default runtime parameters.
|
||||
|
||||
Action:
|
||||
|
||||
@@ -350,8 +347,7 @@ Purpose:
|
||||
|
||||
Action:
|
||||
|
||||
- Add a pipeline parity test under `tests/local_tests/<family>/`
|
||||
(e.g., `tests/local_tests/<family>/test_<family>_pipeline_parity.py`).
|
||||
- Add a pipeline parity test under `tests/local_tests/pipelines/`.
|
||||
- See the [Testing Guide](testing.md) for test conventions.
|
||||
|
||||
### 7) Add user‑facing examples
|
||||
@@ -478,7 +474,7 @@ FastVideo integration.
|
||||
3. Pipeline wiring.
|
||||
- Pipeline: `fastvideo/pipelines/basic/wan/wan_pipeline.py`
|
||||
- Pipeline config: `fastvideo/configs/pipelines/wan.py`
|
||||
- Sampling defaults: `fastvideo/pipelines/basic/wan/profiles.py`
|
||||
- Sampling defaults: `fastvideo/configs/sample/wan.py`
|
||||
|
||||
4. Minimal example.
|
||||
- Script: `examples/inference/basic/basic.py`
|
||||
|
||||
@@ -99,7 +99,7 @@ cd /FastVideo
|
||||
**Install the package**
|
||||
|
||||
```bash
|
||||
uv pip install -e ".[dev]"
|
||||
uv pip install -e .[dev]
|
||||
```
|
||||
|
||||
The Docker image already includes Flash Attention and most heavy dependencies, so this is fast.
|
||||
|
||||
@@ -1,559 +0,0 @@
|
||||
# Porting Eval Metrics into `fastvideo.eval`
|
||||
|
||||
This guide is for contributors adding new evaluation metrics to
|
||||
FastVideo's eval suite. To run the existing metrics, see
|
||||
[`fastvideo/eval/README.md`](../../fastvideo/eval/README.md).
|
||||
|
||||
## When to use this guide
|
||||
|
||||
Use this guide when you are:
|
||||
|
||||
- Adding a new metric (native or wrapping a third-party library).
|
||||
- Porting a benchmark (e.g. VBench, MIND, EvalCrafter) whose Python
|
||||
code needs to be importable from a pinned upstream.
|
||||
- Adding a new metric group (audio, vlm, etc.).
|
||||
|
||||
## TL;DR
|
||||
|
||||
Metrics are auto-discovered from
|
||||
`fastvideo/eval/metrics/<group>/<name>/metric.py`. Each declares itself
|
||||
with `@register("<group>.<name>")` and subclasses `BaseMetric`. Three
|
||||
recipes:
|
||||
|
||||
1. **Native metric** (pure-PyTorch, no submodule). Drop a file,
|
||||
declare deps, implement `compute(sample)`.
|
||||
2. **Library-wrapped metric** (CLIP, torch.hub, transformers, pyiqa).
|
||||
Same as above, plus route the library's cache through
|
||||
`get_cache_dir()` if it has a `download_root=` / `cache_dir=`
|
||||
kwarg.
|
||||
3. **Upstream-submodule-wrapped metric** (vbench-style). Pin upstream
|
||||
as a git submodule under `fastvideo/third_party/eval/<bench>/`. The
|
||||
adapter `__init__.py` does the `sys.path` insert and any runtime
|
||||
compat shims for modern dep versions. Patches live as Python in
|
||||
that file rather than as on-disk patches to the submodule.
|
||||
|
||||
The full recipes are below.
|
||||
|
||||
---
|
||||
|
||||
## 0) Layout and auto-discovery
|
||||
|
||||
```
|
||||
fastvideo/eval/metrics/
|
||||
├── base.py # BaseMetric + lifecycle contract
|
||||
├── common/ # group: SSIM, PSNR, LPIPS
|
||||
├── optical_flow/ # group: gt_optical_flow, synthetic_optical_flow
|
||||
├── vlm/ # group: VideoScore-2
|
||||
├── physics_iq/ # group + sub-metrics
|
||||
└── vbench/ # group: 16 sub-metrics
|
||||
├── __init__.py # sys.path bootstrap + runtime compat shims
|
||||
├── _grit_helper.py # shared upstream-touching helpers
|
||||
└── <sub_metric>/metric.py
|
||||
```
|
||||
|
||||
Auto-discovery (`fastvideo/eval/metrics/__init__.py`) walks each group
|
||||
dir and imports every `metric.py` it finds, which fires the
|
||||
`@register` decorators. Names starting with `_` are skipped. Use that
|
||||
prefix for shared helpers or vendored code that should not register
|
||||
itself.
|
||||
|
||||
---
|
||||
|
||||
## 1) The `BaseMetric` contract
|
||||
|
||||
Every metric subclasses `fastvideo.eval.metrics.base.BaseMetric` and
|
||||
declares:
|
||||
|
||||
```python
|
||||
class YourMetric(BaseMetric):
|
||||
name: str = "common.your_metric" # must match @register
|
||||
requires_reference: bool = True # needs sample["reference"]
|
||||
higher_is_better: bool = True # for ranking / aggregates
|
||||
dependencies: list[str] = [] # importable module names;
|
||||
# registry surfaces a clean
|
||||
# ImportError if missing
|
||||
needs_gpu: bool = False
|
||||
backbone: str | None = None # e.g. "clip_vit_l14"
|
||||
```
|
||||
|
||||
You must implement:
|
||||
|
||||
```python
|
||||
def compute(self, sample: dict) -> list[MetricResult]:
|
||||
"""sample['video'] is (1, T, C, H, W). Return a one-element list.
|
||||
|
||||
The leading 1 is preserved for forward-compat with batched eval;
|
||||
today :class:`EvalWorker` always invokes metrics with B=1.
|
||||
"""
|
||||
```
|
||||
|
||||
You may override:
|
||||
|
||||
- `setup(self) -> None`. Eager model loading. Called once by
|
||||
`create_evaluator`. Idempotent (re-entrant). Use the `if self._model
|
||||
is not None: return` pattern.
|
||||
- `to(self, device)`. Move the metric and its submodels to `device`.
|
||||
|
||||
If a required input is missing (e.g. an fps-aware metric called
|
||||
without `fps`), return `self._skip(sample, reason)` instead of
|
||||
raising.
|
||||
|
||||
---
|
||||
|
||||
## 2) Recipe A: native metric (no external deps)
|
||||
|
||||
Smallest case. Pixel math, simple closed-form.
|
||||
|
||||
```python
|
||||
# fastvideo/eval/metrics/common/your_metric/metric.py
|
||||
from __future__ import annotations
|
||||
import torch
|
||||
from fastvideo.eval.metrics.base import BaseMetric
|
||||
from fastvideo.eval.registry import register
|
||||
from fastvideo.eval.types import MetricResult
|
||||
|
||||
|
||||
@register("common.your_metric")
|
||||
class YourMetric(BaseMetric):
|
||||
name = "common.your_metric"
|
||||
requires_reference = True
|
||||
higher_is_better = True
|
||||
needs_gpu = False
|
||||
dependencies: list[str] = [] # nothing extra
|
||||
|
||||
def compute(self, sample: dict) -> list[MetricResult]:
|
||||
gen, ref = sample["video"], sample["reference"] # (B,T,C,H,W) each
|
||||
per_video = ((gen - ref) ** 2).mean(dim=(1, 2, 3, 4)).sqrt()
|
||||
return [
|
||||
MetricResult(name=self.name, score=float(s), details={})
|
||||
for s in per_video
|
||||
]
|
||||
```
|
||||
|
||||
That is the whole recipe. Drop the file and the registry picks it up.
|
||||
|
||||
---
|
||||
|
||||
## 3) Recipe B: library-wrapped metric (CLIP, torch.hub, transformers, pyiqa)
|
||||
|
||||
If your metric loads a backbone from a Python package, route the
|
||||
library at the eval cache so users get one knob (`FASTVIDEO_EVAL_CACHE`)
|
||||
to redirect everything.
|
||||
|
||||
### Cache routing rules
|
||||
|
||||
| Library | How to route | Location after redirect |
|
||||
|---|---|---|
|
||||
| `clip.load("ViT-X")` | pass `download_root=str(get_cache_dir() / "clip")` | `${FASTVIDEO_EVAL_CACHE}/clip/` |
|
||||
| `torch.hub.load(...)` | nothing; `TORCH_HOME` is redirected at `fastvideo.eval` import time | `${FASTVIDEO_EVAL_CACHE}/torch/hub/` |
|
||||
| `transformers.from_pretrained(...)` | nothing; leave HF's default cache (`~/.cache/huggingface/hub/`) so users dedupe with other ML projects | `~/.cache/huggingface/hub/` |
|
||||
| `huggingface_hub.snapshot_download` / `hf_hub_download` | use `ensure_checkpoint(...)` (it wraps these with filelock) | same as above |
|
||||
| `pyiqa.create_metric(...)` | no env var or kwarg honored; document in metric docstring | pyiqa-internal |
|
||||
| `lpips`, `ptlflow` | torch.hub-based, auto-redirected | `${FASTVIDEO_EVAL_CACHE}/torch/hub/` |
|
||||
| Raw URL (no HF Hub) | use `ensure_checkpoint(name, source="https://...")` | `${FASTVIDEO_EVAL_CACHE}/models/<name>` |
|
||||
| Dataset asset (raw video/mask/image) auto-fetched from a public bucket | download into `get_cache_dir() / "datasets" / "<bench>"`, mirroring upstream's relative layout. Vendor any small manifest (CSV/JSON ≤1 MB) under the metric folder so the dataset can be used without external setup. | `${FASTVIDEO_EVAL_CACHE}/datasets/<bench>/` |
|
||||
|
||||
### Dataset assets: vendor the manifest, auto-fetch the rest
|
||||
|
||||
If your metric ships with its own paired-reference dataset (Physics-IQ
|
||||
is the canonical example), follow this layout:
|
||||
|
||||
- **Manifest** (CSV/JSON ≤1 MB): vendor it under
|
||||
`fastvideo/eval/metrics/<bench>/_vendored/<manifest>.<ext>`, with a
|
||||
sibling `_vendored/LICENSE` recording attribution and provenance.
|
||||
The `_vendored/` subdir is the project-wide convention for
|
||||
upstream-provenance files: it is auto-skipped by metric discovery
|
||||
(the `_` prefix) and by codespell (one `*/_vendored/*` glob in
|
||||
`[tool.codespell].skip`), so dropping in a new vendored file
|
||||
requires no further config. Read the manifest from the dataset
|
||||
module via a `Path(__file__)`-relative resolver. Mirror
|
||||
`_VENDORED_DESCRIPTIONS_CSV` in
|
||||
`fastvideo/eval/datasets/physics_iq.py`.
|
||||
- **Heavy assets** (videos, masks, images): do not vendor. Auto-fetch
|
||||
on first miss into `get_cache_dir() / "datasets" / "<bench>"`,
|
||||
mirroring upstream's relative directory layout one-for-one so a
|
||||
pre-downloaded mirror at any path works as a drop-in
|
||||
`dataset_root=`. Use atomic `.part` then final-rename to be safe
|
||||
under concurrent SLURM ranks.
|
||||
- **Bucket override**: expose `FASTVIDEO_<BENCH>_BUCKET_URL` so users
|
||||
with internal mirrors can redirect.
|
||||
- **Opt-out**: accept `auto_download: bool = True` in the dataset
|
||||
constructor; on `False`, raise `FileNotFoundError` instead of
|
||||
fetching. This covers air-gapped runs and CI.
|
||||
|
||||
The end-state is `get_dataset("<bench>")` with no kwargs.
|
||||
|
||||
### Example: CLIP backbone + LAION head
|
||||
|
||||
```python
|
||||
# fastvideo/eval/metrics/your_group/your_metric/metric.py
|
||||
from __future__ import annotations
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from fastvideo.eval.metrics.base import BaseMetric
|
||||
from fastvideo.eval.registry import register
|
||||
from fastvideo.eval.types import MetricResult
|
||||
|
||||
|
||||
@register("your_group.your_metric")
|
||||
class YourMetric(BaseMetric):
|
||||
name = "your_group.your_metric"
|
||||
requires_reference = False
|
||||
needs_gpu = True
|
||||
dependencies = ["clip"] # "openai-clip" PyPI; importable as `clip`
|
||||
|
||||
def __init__(self) -> None:
|
||||
super().__init__()
|
||||
self._clip = None
|
||||
self._head = None
|
||||
|
||||
def setup(self) -> None:
|
||||
if self._clip is not None:
|
||||
return
|
||||
import clip
|
||||
from fastvideo.eval.models import ensure_checkpoint, get_cache_dir
|
||||
|
||||
# Backbone: route CLIP's cache through our root.
|
||||
self._clip, _ = clip.load(
|
||||
"ViT-L/14",
|
||||
device=self.device,
|
||||
download_root=str(get_cache_dir() / "clip"),
|
||||
)
|
||||
self._clip.eval()
|
||||
|
||||
# URL-fetched head: ensure_checkpoint downloads to
|
||||
# ${FASTVIDEO_EVAL_CACHE}/models/ with filelock + atomic rename.
|
||||
ckpt = ensure_checkpoint(
|
||||
"your_head.pth",
|
||||
source="https://example.com/path/to/your_head.pth",
|
||||
)
|
||||
self._head = nn.Linear(768, 1)
|
||||
self._head.load_state_dict(
|
||||
torch.load(ckpt, map_location="cpu", weights_only=True)
|
||||
)
|
||||
self._head.to(self.device).eval()
|
||||
|
||||
def to(self, device):
|
||||
super().to(device)
|
||||
if self._clip is not None:
|
||||
self._clip = self._clip.to(self.device)
|
||||
if self._head is not None:
|
||||
self._head = self._head.to(self.device)
|
||||
return self
|
||||
|
||||
def compute(self, sample: dict) -> list[MetricResult]:
|
||||
...
|
||||
```
|
||||
|
||||
### Do not redirect other `~/.cache/...` dirs
|
||||
|
||||
If a third-party library hard-codes `~/.cache/<lib>/` and offers no
|
||||
override, document the exception in the metric's docstring. Forcing
|
||||
redirection by setting `os.environ` or patching `os.path.expanduser`
|
||||
is fragile and breaks user expectations of where the library's cache
|
||||
lives.
|
||||
|
||||
---
|
||||
|
||||
## 4) Recipe C: upstream-submodule-wrapped metric (vbench pattern)
|
||||
|
||||
Use this when the upstream benchmark ships Python code (`vbench/`,
|
||||
`MIND/`, etc.) that is not pip-installable cleanly. See
|
||||
`fastvideo/eval/metrics/vbench/__init__.py` for the worked example.
|
||||
|
||||
### 4.1 Pin the upstream as a submodule
|
||||
|
||||
```bash
|
||||
git submodule add <upstream-url> fastvideo/third_party/eval/<bench>
|
||||
cd fastvideo/third_party/eval/<bench>
|
||||
git checkout <pinned-sha>
|
||||
cd -
|
||||
git add .gitmodules fastvideo/third_party/eval/<bench>
|
||||
```
|
||||
|
||||
The submodule pulls under the standard `git submodule update --init
|
||||
--recursive` flow that users already run for kernel deps.
|
||||
|
||||
### 4.2 Bootstrap on `sys.path`
|
||||
|
||||
```python
|
||||
# fastvideo/eval/metrics/<bench>/__init__.py
|
||||
from __future__ import annotations
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# fastvideo/eval/metrics/<bench>/__init__.py → ../../../../third_party/eval/<bench>
|
||||
_UPSTREAM = Path(__file__).resolve().parents[3] / "third_party" / "eval" / "<bench>"
|
||||
if _UPSTREAM.is_dir() and str(_UPSTREAM) not in sys.path:
|
||||
sys.path.insert(0, str(_UPSTREAM))
|
||||
```
|
||||
|
||||
We do not `pip install` the upstream because its egg-link/.pth would
|
||||
just re-do this `sys.path.insert`, and skipping the install also skips
|
||||
the upstream's `setup.py` (which often gates on a specific CUDA
|
||||
version).
|
||||
|
||||
### 4.3 Modern-dep compat: runtime shims
|
||||
|
||||
Upstream code pinned to e.g. `transformers==4.33.2`, `numpy<2`
|
||||
typically breaks against modern versions in 3-4 known places (API
|
||||
renames). Fix those at import time, in the same `__init__.py`:
|
||||
|
||||
```python
|
||||
def _install_compat_shims() -> None:
|
||||
# Example: transformers.modeling_utils API moved.
|
||||
try:
|
||||
import transformers.modeling_utils as _mu
|
||||
import transformers.pytorch_utils as _pu
|
||||
for _n in ("apply_chunking_to_forward",
|
||||
"find_pruneable_heads_and_indices",
|
||||
"prune_linear_layer"):
|
||||
if not hasattr(_mu, _n) and hasattr(_pu, _n):
|
||||
setattr(_mu, _n, getattr(_pu, _n))
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# Example: numpy.lib.function_base.disp removed in numpy>=2.
|
||||
try:
|
||||
import types, numpy.lib as _nl
|
||||
if not hasattr(_nl, "function_base"):
|
||||
_stub = types.ModuleType("numpy.lib.function_base")
|
||||
_stub.disp = lambda *a, **k: None
|
||||
sys.modules["numpy.lib.function_base"] = _stub
|
||||
_nl.function_base = _stub
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
_install_compat_shims()
|
||||
```
|
||||
|
||||
For function-level patches that cannot be expressed as attribute
|
||||
writes (e.g. wrapping a model factory function), use a
|
||||
`sys.meta_path` finder that wraps the loader. See
|
||||
`_install_modeling_finetune_hook()` in
|
||||
`fastvideo/eval/metrics/vbench/__init__.py` for the pattern (about 30
|
||||
lines).
|
||||
|
||||
Why shims rather than `git apply` patches: patches go stale when the
|
||||
upstream SHA changes; shims are versioned Python code in our repo,
|
||||
they are grep-able, and they only run if the targeted module is
|
||||
imported.
|
||||
|
||||
### 4.4 Per-sub-metric files
|
||||
|
||||
Each sub-metric is a normal `BaseMetric` subclass that imports from
|
||||
the upstream:
|
||||
|
||||
```python
|
||||
# fastvideo/eval/metrics/<bench>/<sub>/metric.py
|
||||
from fastvideo.eval.metrics.base import BaseMetric
|
||||
from fastvideo.eval.registry import register
|
||||
from fastvideo.eval.types import MetricResult
|
||||
|
||||
|
||||
@register("<bench>.<sub>")
|
||||
class YourSubMetric(BaseMetric):
|
||||
...
|
||||
|
||||
def setup(self) -> None:
|
||||
if self._model is not None:
|
||||
return
|
||||
# The sys.path bootstrap fired when fastvideo.eval.metrics.<bench>
|
||||
# was imported (which auto-discovery does before importing this
|
||||
# sub-package). Upstream imports just work:
|
||||
from <bench>.something import SomeModel
|
||||
...
|
||||
```
|
||||
|
||||
### 4.5 Conditional registration when the upstream is missing
|
||||
|
||||
If a user installed `fastvideo[eval]` but did not run `git submodule
|
||||
update --init`, `<bench>.*` metrics should not register. The
|
||||
auto-discovery walker imports each sub-package's `metric` module; have
|
||||
that import bail out cleanly:
|
||||
|
||||
```python
|
||||
# fastvideo/eval/metrics/<bench>/__init__.py — at the bottom
|
||||
_AVAILABLE = (_UPSTREAM / "<bench>" / "__init__.py").is_file()
|
||||
```
|
||||
|
||||
```python
|
||||
# fastvideo/eval/metrics/<bench>/<sub>/__init__.py
|
||||
from fastvideo.eval.metrics.<bench> import _AVAILABLE
|
||||
if _AVAILABLE:
|
||||
from .metric import YourSubMetric # noqa
|
||||
```
|
||||
|
||||
`fastvideo eval list` then reflects what the user actually has rather
|
||||
than what they could have.
|
||||
|
||||
### 4.6 Leave the upstream alone unless it blocks the metric
|
||||
|
||||
The upstream is pinned. If a metric works against the pinned SHA,
|
||||
leave the upstream files untouched. If it actively breaks against
|
||||
modern deps (the import-drift cases above), shim it. Avoid
|
||||
fastvideo-side forks of upstream code; they make patches go stale and
|
||||
parity drift.
|
||||
|
||||
---
|
||||
|
||||
## 5) Model checkpoints: `ensure_checkpoint`
|
||||
|
||||
Use `ensure_checkpoint(name, source, filename=None)` for any
|
||||
non-package weights. It resolves a local path, downloading on miss,
|
||||
with filelock safety across processes and SLURM ranks.
|
||||
|
||||
| `source` form | What happens |
|
||||
|---|---|
|
||||
| `"/abs/path/to/file.pth"` | passthrough, returned unchanged |
|
||||
| `"https://..."` | downloaded to `${FASTVIDEO_EVAL_CACHE}/models/<name>` via `huggingface_hub.http_get`, atomic rename, filelock |
|
||||
| `"org/repo"` (no `filename`) | `snapshot_download(repo_id)` → `~/.cache/huggingface/hub/` |
|
||||
| `"org/repo"` (with `filename`) | `hf_hub_download(repo_id, filename)` → `~/.cache/huggingface/hub/` |
|
||||
|
||||
`name` is only used as the local filename for URL sources. HF sources
|
||||
ignore it (HF manages its own cache key by content hash).
|
||||
|
||||
```python
|
||||
from fastvideo.eval.models import ensure_checkpoint
|
||||
|
||||
# URL: name matters
|
||||
ckpt = ensure_checkpoint(
|
||||
"amt-s.pth",
|
||||
source="https://huggingface.co/lalala125/AMT/resolve/main/amt-s.pth",
|
||||
)
|
||||
|
||||
# HF single file: name is decorative
|
||||
ckpt = ensure_checkpoint(
|
||||
"raft-things.pth", # ignored; HF cache uses repo+sha
|
||||
source="OpenGVLab/VBench_Used_Models",
|
||||
filename="raft-things.pth",
|
||||
)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6) Declaring `dependencies`
|
||||
|
||||
Set `dependencies = ["pkg1", "pkg2"]` on your metric class with
|
||||
importable module names (not PyPI distribution names). The registry
|
||||
checks each via `importlib.util.find_spec` at instantiation time and
|
||||
raises a clean `ImportError` pointing the user at the right install
|
||||
extra:
|
||||
|
||||
```python
|
||||
class YourMetric(BaseMetric):
|
||||
dependencies = ["clip", "timm"] # importable as `import clip`, `import timm`
|
||||
```
|
||||
|
||||
If a dep is in `[project.optional-dependencies.eval-<group>]`, you do
|
||||
not need to do anything more. If it is a new dep, add it to that
|
||||
group in `pyproject.toml`.
|
||||
|
||||
---
|
||||
|
||||
## 7) Common gotchas
|
||||
|
||||
- The standard `git submodule update --init --recursive` is enough
|
||||
for a benchmark; do not write a `setup.sh`. Modern-dep compat goes
|
||||
into your `__init__.py` as runtime shims.
|
||||
- Do not modify upstream files on disk. The submodule should always
|
||||
match its pinned SHA. Compat lives in our `__init__.py`.
|
||||
- Do not pip-install the upstream. The egg-link is a glorified
|
||||
`sys.path.insert`, which we do directly in `__init__.py`.
|
||||
- Do not call `torch.hub.set_dir(...)` from your metric. It is done
|
||||
globally in `fastvideo/eval/__init__.py`.
|
||||
- Do not put cache-redirection env vars in your metric's `setup()`.
|
||||
By the time `setup()` runs, the library has likely already cached
|
||||
the default-location decision. Set env vars at package-init time.
|
||||
- Skip rather than raise when an input is missing. Use
|
||||
`self._skip(sample, reason)` for any expected-missing input. It
|
||||
returns a list of `MetricResult(score=None)` so other metrics in
|
||||
the same evaluator continue.
|
||||
- Watch for upstream re-registration conflicts. If the upstream uses
|
||||
a global registry (detectron2's `META_ARCH_REGISTRY`, MMCV, etc.),
|
||||
loading the same model twice in the same process will throw. The
|
||||
evaluator already loads each metric once; if you write a custom
|
||||
setup-then-call pattern, mirror that single-load discipline.
|
||||
|
||||
---
|
||||
|
||||
## 8) Training-time eval: keep evaluators hot, free caches between calls
|
||||
|
||||
When wiring eval into a training loop, the working pattern is:
|
||||
|
||||
1. Construct the `Evaluator` once and attach it to the pipeline
|
||||
(`self._eval = create_evaluator(...)`). Do not recreate it per
|
||||
validation round; that re-pays the model load cost.
|
||||
2. Save validation videos to disk (the diffusion path already does
|
||||
this). Pass paths to `evaluator.evaluate`, not in-memory tensors
|
||||
that share GPU memory with the training model.
|
||||
3. Run validation only on rank 0 of each sequence-parallel group.
|
||||
Gather paths from other ranks and let rank 0 score everything.
|
||||
4. After every `evaluate(...)` call, call
|
||||
`evaluator.release_cuda_memory()` in a `finally` block. That runs
|
||||
`gc.collect()` + `torch.cuda.empty_cache()` +
|
||||
`torch.cuda.ipc_collect()`. The eval model stays loaded; only
|
||||
transient activation buffers from the just-finished call get
|
||||
freed:
|
||||
|
||||
```python
|
||||
for video_path in batch:
|
||||
try:
|
||||
scores = self._eval.evaluate(video=load_video(video_path))
|
||||
finally:
|
||||
self._eval.release_cuda_memory()
|
||||
```
|
||||
|
||||
5. If memory pressure spikes (rare on H200), call
|
||||
`evaluator.unload()` to drop every metric reference and let the
|
||||
GPU memory be GC'd. `unload` is reversible:
|
||||
`evaluator.reload()` rebuilds the same metrics with the original
|
||||
config (re-paying the model load cost). Calling `evaluate`
|
||||
between `unload` and `reload` raises a clear `RuntimeError`.
|
||||
|
||||
For most metrics (sub-1 GB backbones, e.g. CLIP/DINO/RAFT/AMT) the
|
||||
eval model can stay co-resident with the training model in
|
||||
`transformer.eval()` mode without any swap. For larger ones
|
||||
(VideoScore2 at 14 GB), measure first; if it fits on the rank-0 GPU
|
||||
during validation (training model in eval mode means no
|
||||
grads/optimizer updates), keep it hot. If not, `unload` between
|
||||
rounds.
|
||||
|
||||
## 9) Local verification
|
||||
|
||||
Native and library-wrapped metrics: a single-GPU smoke is enough.
|
||||
|
||||
```python
|
||||
import torch
|
||||
from fastvideo.eval import create_evaluator
|
||||
|
||||
ev = create_evaluator(metrics=["<group>.<your_metric>"], device="cuda")
|
||||
video = torch.randn(1, 49, 3, 256, 256, device="cuda").clamp(0, 1)
|
||||
print(ev.evaluate(video=video))
|
||||
```
|
||||
|
||||
Submodule-wrapped metrics: also do a parity check against the
|
||||
upstream once. Clone upstream into a separate venv, run the same
|
||||
video through both, and expect an exact match on bit-deterministic
|
||||
metrics and ≤1% drift on backbone-heavy ones (driven by
|
||||
transformers/torch version differences).
|
||||
|
||||
For quick parity in CI: pin a tiny test video, record expected
|
||||
scores ± tolerance, and add a calibration test under
|
||||
`fastvideo/tests/eval/`.
|
||||
|
||||
---
|
||||
|
||||
## 10) When not to add a metric
|
||||
|
||||
- **Set-vs-set distribution metrics** (FVD, FID-style) do not fit
|
||||
`BaseMetric.compute(sample)` cleanly; they need a population.
|
||||
Adding them requires a stateful accumulator interface that does
|
||||
not exist yet. Open an issue first.
|
||||
- **Metrics requiring a single-GPU model larger than available
|
||||
memory.** Eval is not the place for tensor-parallel sharding;
|
||||
metrics are expected to fit on one GPU.
|
||||
- **Metrics that need `mmcv` with a conflicting CUDA ABI.** Document
|
||||
the affected sub-metrics as unsupported and skip them. Building
|
||||
isolation infrastructure (subprocess engine, per-metric venv) is
|
||||
out of scope.
|
||||
@@ -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
|
||||
|
||||
@@ -25,12 +25,10 @@ Mergify before any merge is allowed.
|
||||
| `[refactor]` | Code restructuring with no behavior change |
|
||||
| `[perf]` | Performance improvement |
|
||||
| `[ci]` | CI/CD or build tooling changes |
|
||||
| `[infra]` | Repo infrastructure: agent tooling, debug hooks, conversion scripts, dev infra |
|
||||
| `[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 |
|
||||
| `[skill]` or `[skills]` | Agent skills under `.agents/skills/` or `.claude/skills/` |
|
||||
|
||||
**Examples:**
|
||||
|
||||
@@ -40,8 +38,6 @@ Mergify before any merge is allowed.
|
||||
[refactor] Restructure distributed attention dispatch
|
||||
[docs] Add LoRA finetuning guide
|
||||
[new-model] Port HunyuanVideo 1.5 to FastVideo
|
||||
[infra] Add activation trace hooks for pipeline debugging
|
||||
[skill] Add add-model agent skill
|
||||
```
|
||||
|
||||
If your title is missing the tag, Mergify will post a comment listing the valid formats.
|
||||
@@ -55,8 +51,8 @@ Labels are applied automatically based on your PR title and the files you change
|
||||
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: infra`,
|
||||
`type: docs`, `type: misc`, `type: new-model`, `type: skill`
|
||||
`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`,
|
||||
@@ -191,8 +187,8 @@ Common quick fixes:
|
||||
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`, `infra`, `doc`,
|
||||
`docs`, `misc`, `chore`, `kernel`, `new-model`, `skill`, `skills`
|
||||
Valid tags: `feat`, `feature`, `bugfix`, `fix`, `refactor`, `perf`, `ci`, `doc`, `docs`,
|
||||
`misc`, `chore`, `kernel`, `new-model`
|
||||
|
||||
### My PR has merge conflicts (`needs-rebase` label)
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
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."
|
||||
profile_owned: "Public field remains supported only through a model/profile-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."
|
||||
@@ -29,7 +29,7 @@ surfaces:
|
||||
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
|
||||
torch_compile_kwargs: generator.engine.compile.kwargs
|
||||
disable_autocast: generator.engine.disable_autocast
|
||||
enable_stage_verification: generator.engine.enable_stage_verification
|
||||
prompt_txt: request.inputs.prompt_path
|
||||
@@ -40,12 +40,12 @@ surfaces:
|
||||
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
|
||||
profile_owned:
|
||||
ltx2_vae_tiling: generator.pipeline.profile_overrides.ltx2.vae_tiling
|
||||
ltx2_vae_spatial_tile_size_in_pixels: generator.pipeline.profile_overrides.ltx2.vae.spatial_tile_size_in_pixels
|
||||
ltx2_vae_spatial_tile_overlap_in_pixels: generator.pipeline.profile_overrides.ltx2.vae.spatial_tile_overlap_in_pixels
|
||||
ltx2_vae_temporal_tile_size_in_frames: generator.pipeline.profile_overrides.ltx2.vae.temporal_tile_size_in_frames
|
||||
ltx2_vae_temporal_tile_overlap_in_frames: generator.pipeline.profile_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."
|
||||
@@ -69,16 +69,16 @@ surfaces:
|
||||
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
|
||||
profile_owned:
|
||||
embedded_cfg_scale: generator.pipeline.profile_overrides.embedded_cfg_scale
|
||||
flow_shift: generator.pipeline.profile_overrides.flow_shift
|
||||
flow_shift_sr: generator.pipeline.profile_overrides.flow_shift_sr
|
||||
is_causal: generator.pipeline.profile_overrides.is_causal
|
||||
vae_tiling: generator.pipeline.profile_overrides.vae_tiling
|
||||
vae_sp: generator.pipeline.profile_overrides.vae_sp
|
||||
dmd_denoising_steps: generator.pipeline.profile_overrides.dmd_denoising_steps
|
||||
ti2v_task: generator.pipeline.profile_overrides.ti2v_task
|
||||
boundary_ratio: generator.pipeline.profile_overrides.boundary_ratio
|
||||
compatibility_only:
|
||||
model_path: "Redundant with generator.model_path."
|
||||
disable_autocast: "Duplicated by generator.engine.disable_autocast during migration."
|
||||
@@ -97,7 +97,7 @@ surfaces:
|
||||
postprocess_text_funcs: "Internal text postprocessing hooks."
|
||||
|
||||
pipeline_config_extensions:
|
||||
preset_owned:
|
||||
profile_owned:
|
||||
conditioning_strategy:
|
||||
sources:
|
||||
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
||||
@@ -306,35 +306,11 @@ surfaces:
|
||||
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."
|
||||
guidance_scale: "Gen3C pipeline-level default pending profile/default-request cleanup."
|
||||
num_inference_steps: "Gen3C pipeline-level default pending profile/default-request cleanup."
|
||||
internal_only:
|
||||
audio_decoder_config: "Legacy internal component config object."
|
||||
audio_decoder_precision: "Precision override pending dedicated component precision design."
|
||||
@@ -369,7 +345,6 @@ surfaces:
|
||||
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
|
||||
@@ -378,43 +353,96 @@ surfaces:
|
||||
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:
|
||||
profile_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: {}
|
||||
sampling_param_extensions:
|
||||
moved:
|
||||
guidance_scale_2:
|
||||
target: request.sampling.guidance_scale_2
|
||||
sources:
|
||||
- fastvideo.configs.sample.lingbotworld.LingBotWorld_SamplingParam
|
||||
- fastvideo.configs.sample.lingbotworld.Wan2_2_I2V_A14B_SamplingParam
|
||||
- fastvideo.configs.sample.wan.SelfForcingWan2_2_T2V_A14B_480P_SamplingParam
|
||||
- fastvideo.configs.sample.wan.Wan2_2_I2V_A14B_SamplingParam
|
||||
- fastvideo.configs.sample.wan.Wan2_2_T2V_A14B_SamplingParam
|
||||
profile_owned:
|
||||
action_list:
|
||||
target: request.extensions.hunyuangamecraft.action_list
|
||||
sources:
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraftSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft65FrameSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft129FrameSamplingParam
|
||||
action_speed_list:
|
||||
target: request.extensions.hunyuangamecraft.action_speed_list
|
||||
sources:
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraftSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft65FrameSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft129FrameSamplingParam
|
||||
camera_states:
|
||||
target: request.extensions.hunyuangamecraft.camera_states
|
||||
sources:
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraftSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft65FrameSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft129FrameSamplingParam
|
||||
camera_trajectory:
|
||||
target: request.extensions.hunyuangamecraft.camera_trajectory
|
||||
sources:
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraftSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft65FrameSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft129FrameSamplingParam
|
||||
conditioning_mask:
|
||||
target: request.extensions.hunyuangamecraft.conditioning_mask
|
||||
sources:
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraftSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft65FrameSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft129FrameSamplingParam
|
||||
gt_latents:
|
||||
target: request.extensions.hunyuangamecraft.gt_latents
|
||||
sources:
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraftSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft65FrameSamplingParam
|
||||
- fastvideo.configs.sample.hunyuangamecraft.HunyuanGameCraft129FrameSamplingParam
|
||||
prompt_attention_mask:
|
||||
target: request.extensions.hyworld.prompt_attention_mask
|
||||
sources: [fastvideo.configs.sample.hyworld.HYWorld_SamplingParam]
|
||||
negative_attention_mask:
|
||||
target: request.extensions.hyworld.negative_attention_mask
|
||||
sources: [fastvideo.configs.sample.hyworld.HYWorld_SamplingParam]
|
||||
ltx2_cfg_scale_audio:
|
||||
target: request.extensions.ltx2.cfg_scale_audio
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_cfg_scale_video:
|
||||
target: request.extensions.ltx2.cfg_scale_video
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_modality_scale_audio:
|
||||
target: request.extensions.ltx2.modality_scale_audio
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_modality_scale_video:
|
||||
target: request.extensions.ltx2.modality_scale_video
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_rescale_scale:
|
||||
target: request.extensions.ltx2.rescale_scale
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_stg_blocks_audio:
|
||||
target: request.extensions.ltx2.stg_blocks_audio
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_stg_blocks_video:
|
||||
target: request.extensions.ltx2.stg_blocks_video
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_stg_scale_audio:
|
||||
target: request.extensions.ltx2.stg_scale_audio
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
ltx2_stg_scale_video:
|
||||
target: request.extensions.ltx2.stg_scale_video
|
||||
sources: [fastvideo.configs.sample.ltx2.LTX2BaseSamplingParam]
|
||||
|
||||
openai_image_request:
|
||||
kept:
|
||||
|
||||
@@ -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/api/sampling_param.py`: runtime sampling parameters.
|
||||
- `fastvideo/configs/sample/*`: default 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.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample 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)
|
||||
@@ -49,9 +49,8 @@ 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/api/sampling_param.py`: sampling parameters (steps, frames,
|
||||
guidance scale, resolution, fps). Defaults come from profiles in
|
||||
`fastvideo/pipelines/basic/<family>/profiles.py`.
|
||||
- `fastvideo/configs/sample/`: default sampling parameters (steps, frames,
|
||||
guidance scale, resolution, fps).
|
||||
- `fastvideo/registry.py`: unified registry for pipeline config + sampling
|
||||
defaults and model metadata resolution, defined via explicit
|
||||
`register_configs(...)` blocks (no separate dict registries).
|
||||
@@ -143,7 +142,7 @@ 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/pipelines/basic/wan/profiles.py`
|
||||
- Sampling defaults -> `fastvideo/configs/sample/wan.py`
|
||||
|
||||
## Pipeline system
|
||||
|
||||
|
||||
@@ -1,177 +0,0 @@
|
||||
# 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`.
|
||||
@@ -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 \
|
||||
|
||||
@@ -86,25 +86,3 @@ 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.
|
||||
|
||||
@@ -27,7 +27,7 @@ uv pip install fastvideo
|
||||
conda create -n fastvideo python=3.12 -y
|
||||
conda activate fastvideo
|
||||
|
||||
uv pip install fastvideo
|
||||
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 (still drives installs through `uv`):
|
||||
Alternative with Conda environment:
|
||||
|
||||
```bash
|
||||
uv pip install -e .
|
||||
uv pip install flash-attn --no-build-isolation -v
|
||||
pip install -e .
|
||||
pip install flash-attn --no-build-isolation -v
|
||||
```
|
||||
|
||||
## Hardware Requirements
|
||||
|
||||
@@ -58,16 +58,14 @@ 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
|
||||
uv pip install fastvideo
|
||||
pip install fastvideo
|
||||
```
|
||||
|
||||
Also optionally install FlashAttention:
|
||||
|
||||
```bash
|
||||
uv pip install flash-attn --no-build-isolation -v
|
||||
pip install flash-attn --no-build-isolation -v
|
||||
```
|
||||
|
||||
### Installation from Source
|
||||
@@ -89,7 +87,7 @@ uv pip install -e .
|
||||
Alternative with Conda environment:
|
||||
|
||||
```bash
|
||||
uv pip install -e .
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
### Optional Dependencies
|
||||
@@ -103,7 +101,7 @@ uv pip install flash-attn --no-build-isolation -v
|
||||
Alternative with Conda environment:
|
||||
|
||||
```bash
|
||||
uv pip install flash-attn --no-build-isolation -v
|
||||
pip install flash-attn --no-build-isolation -v
|
||||
```
|
||||
|
||||
## Set up using Docker
|
||||
|
||||
@@ -57,10 +57,8 @@ 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
|
||||
uv pip install fastvideo
|
||||
pip install fastvideo
|
||||
```
|
||||
|
||||
### Installation from Source
|
||||
@@ -82,7 +80,7 @@ uv pip install -e .
|
||||
Alternative with Conda environment:
|
||||
|
||||
```bash
|
||||
uv pip install -e .
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
## Development Environment Setup
|
||||
|
||||
@@ -33,7 +33,7 @@ The following two classes `PipelineConfig` and `SamplingParam` are used to confi
|
||||
|
||||
### SamplingParam
|
||||
|
||||
::: fastvideo.api.sampling_param.SamplingParam
|
||||
::: fastvideo.configs.sample.base.SamplingParam
|
||||
options:
|
||||
show_root_heading: true
|
||||
show_source: false
|
||||
|
||||
@@ -128,14 +128,19 @@ Concrete hierarchy: `DiTConfig` → `DiTArchConfig`, `VAEConfig` →
|
||||
- `dump_to_json()` / `load_from_json()` — JSON persistence. Callable
|
||||
fields and `arch_config` are excluded from dumps.
|
||||
|
||||
### SamplingParam (`fastvideo/api/sampling_param.py`)
|
||||
### SamplingParam (`fastvideo/configs/sample/`)
|
||||
|
||||
Generation parameters separate from pipeline config. Each model family
|
||||
provides defaults via a profile (see `fastvideo/pipelines/basic/<family>/profiles.py`):
|
||||
provides defaults:
|
||||
|
||||
```python
|
||||
sp = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
|
||||
# sp.height == 480, sp.width == 832, sp.num_frames == 81, etc.
|
||||
@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
|
||||
```
|
||||
|
||||
## Component Loading
|
||||
@@ -425,9 +430,9 @@ User: generator.generate_video(prompt, ...)
|
||||
`fastvideo/configs/pipelines/<model>.py`. Set DiT/VAE/encoder configs,
|
||||
flow_shift, precision defaults.
|
||||
|
||||
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.
|
||||
2. **Sampling param** — Create a `SamplingParam` subclass in
|
||||
`fastvideo/configs/sample/<model>.py`. Set 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
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
- Install MoGe:
|
||||
|
||||
```bash
|
||||
uv pip install git+https://github.com/microsoft/MoGe.git
|
||||
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:
|
||||
@@ -89,7 +89,7 @@ GEN3C defaults in FastVideo:
|
||||
|
||||
These values are defined in:
|
||||
|
||||
- `fastvideo/pipelines/basic/gen3c/profiles.py`
|
||||
- `fastvideo/configs/sample/gen3c.py`
|
||||
- `fastvideo/configs/pipelines/gen3c.py`
|
||||
|
||||
and align with the official GEN3C inference defaults in:
|
||||
|
||||
@@ -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
|
||||
uv pip install flash-attn==2.7.4.post1 --no-build-isolation
|
||||
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
|
||||
uv pip install ninja
|
||||
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 uv pip install -e .
|
||||
python setup.py install # or pip install -e .
|
||||
```
|
||||
|
||||
### Sage Attention 3
|
||||
|
||||
@@ -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
|
||||
uv pip install vsa
|
||||
pip install vsa
|
||||
```
|
||||
|
||||
### 1. Download dataset:
|
||||
|
||||
@@ -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
|
||||
uv pip install vsa
|
||||
pip install vsa
|
||||
```
|
||||
|
||||
### Data-free Distillation
|
||||
|
||||
@@ -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
|
||||
uv pip install vsa
|
||||
pip install vsa
|
||||
```
|
||||
|
||||
### 1. Download dataset:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples"
|
||||
def main():
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
|
||||
def main():
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
|
||||
def main():
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
|
||||
def main():
|
||||
|
||||
@@ -2,7 +2,7 @@ import os
|
||||
import time
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_dmd2"
|
||||
def main():
|
||||
|
||||
@@ -7,7 +7,7 @@ and the GEN3C diffusion model.
|
||||
|
||||
Requirements:
|
||||
1. Install MoGe:
|
||||
uv pip install git+https://github.com/microsoft/MoGe.git
|
||||
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:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
import json
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_hy15"
|
||||
def main():
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
import json
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_hy15_1080p"
|
||||
def main():
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.models.dits.lingbotworld.cam_utils import prepare_camera_embedding
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
OUTPUT_PATH = "video_samples_lingbotworld"
|
||||
def main():
|
||||
# FastVideo will automatically use the optimal default arguments for the
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from fastvideo import VideoGenerator, PipelineConfig
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
def main():
|
||||
config = PipelineConfig.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples"
|
||||
def main():
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from fastvideo import VideoGenerator, SamplingParam
|
||||
import json
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_i2v"
|
||||
def main():
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_t2v"
|
||||
def main():
|
||||
|
||||
@@ -1,77 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
"""Stable Audio Open 1.0 — text-to-audio (baseline) example.
|
||||
|
||||
User story (game-audio designer, prototyping):
|
||||
"I'm prototyping a level and I need 6 seconds of background
|
||||
ambience — gentle wind, distant thunder, a hint of birdsong. I
|
||||
don't want to dig through a sound library; I want to type what I
|
||||
hear in my head and get a wav back. If it's wrong I'll iterate
|
||||
on the prompt. This is the first stop."
|
||||
|
||||
User story (musician sketching ideas):
|
||||
"I want to bounce a 30s lo-fi drum loop to use as a placeholder
|
||||
bed while I build the rest of the track. Type prompt, get audio,
|
||||
drop into the DAW. The actual production beat I'll record
|
||||
myself, but I need *something* to write the chords against."
|
||||
|
||||
User story (researcher exploring the model):
|
||||
"First time touching Stable Audio Open — what does it sound
|
||||
like at default settings? This is the smallest amount of code
|
||||
that goes from prompt to mp4."
|
||||
|
||||
How it works:
|
||||
Pure text-to-audio (T2A). The pipeline runs:
|
||||
T5 + NumberConditioner -> StableAudioDiT -> Oobleck VAE
|
||||
via the `dpmpp-3m-sde` k-diffusion sampler. All components are
|
||||
FastVideo-native — no diffusers / transformers model imports at
|
||||
runtime (see REVIEW item 30). Mirrors upstream
|
||||
`stable_audio_tools.inference.generation.generate_diffusion_cond`
|
||||
bit-for-bit (~0.2% abs_mean drift on 25 steps).
|
||||
|
||||
Tunable knobs (the "creative dials"):
|
||||
audio_end_in_s
|
||||
1–6 — quick ideation (sub-10s wall clock at 100 steps)
|
||||
10–30 — full musical phrase / loop length (the README example
|
||||
uses 30s)
|
||||
47.5 — model maximum (full sample_size = 2097152 / 44100 Hz)
|
||||
num_inference_steps
|
||||
25 — fast preview, occasional artifacts
|
||||
100 — preset default (matches the HF model card)
|
||||
250 — diminishing returns past here
|
||||
guidance_scale
|
||||
3 — looser, more variation per seed
|
||||
7 — preset default; matches README
|
||||
12+ — sharper but can sound "fried"
|
||||
|
||||
Prerequisites:
|
||||
1. Accept the terms on https://huggingface.co/stabilityai/stable-audio-open-1.0
|
||||
and export your HF token in the shell:
|
||||
export HF_TOKEN=hf_...
|
||||
2. Install optional inference deps (one-time):
|
||||
uv pip install k_diffusion einops_exts alias_free_torch torchsde
|
||||
"""
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
PROMPT = "Lo-fi hip hop instrumental with vinyl crackle and gentle piano."
|
||||
|
||||
|
||||
def main() -> None:
|
||||
generator = VideoGenerator.from_pretrained(
|
||||
"FastVideo/stable-audio-open-1.0-Diffusers",
|
||||
num_gpus=1,
|
||||
)
|
||||
output_path = "outputs_audio/stable_audio_basic/output_stable_audio.wav"
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
output_path=output_path,
|
||||
save_video=True,
|
||||
# 6-second clip; the model max is ~47.5s.
|
||||
audio_end_in_s=6.0,
|
||||
# The registered preset gives 100 steps + CFG=7.0 by default;
|
||||
# override num_inference_steps / guidance_scale here for QA.
|
||||
)
|
||||
generator.shutdown()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,77 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
"""Stable Audio Open 1.0 — audio-to-audio variation example.
|
||||
|
||||
User story (musician, late at night):
|
||||
"I generated this 12-second lo-fi loop earlier and I love the chord
|
||||
progression and overall vibe, but the snare hit at 0:08 sounds wrong
|
||||
and the rhythm feels stiff. I don't want to start over from scratch
|
||||
and lose what's working — I want the model to keep the harmony and
|
||||
mood but reroll the percussion + groove."
|
||||
|
||||
User story (sound designer, on a deadline):
|
||||
"I have one good 'sword clang' SFX. The art director wants 8 sibling
|
||||
variations that all feel like the same sword from different angles —
|
||||
same metal, same weight, slightly different impact. I'd rather
|
||||
refine my one good take than text-prompt my way through 50 misses."
|
||||
|
||||
Pass `init_audio=path/to/clip` (any wav/mp3/mp4/m4a/flac the standard
|
||||
deps decode) and the model will use it as a starting point for the
|
||||
text prompt instead of pure noise.
|
||||
|
||||
Picking `init_audio_strength` (0.0 to 1.0):
|
||||
|
||||
Higher = closer to the source clip. Lower = more transformation.
|
||||
(Same convention as the "Input Audio Strength" slider in
|
||||
Stability's commercial Stable Audio web UI, so values transfer
|
||||
directly.)
|
||||
|
||||
| strength | what you get |
|
||||
|----------|----------------------------------------------------|
|
||||
| 1.00 | Output ≈ reference. No transformation. |
|
||||
| 0.85 | Texture micro-variation only. |
|
||||
| 0.70 | Light reroll, same instruments. |
|
||||
| 0.60 | Default. Instrument identity is replaceable |
|
||||
| | (cello can take over from piano on the same notes).|
|
||||
| 0.50 | Heavy — only melody / chord progression survives. |
|
||||
| 0.30 | Reference acts as a loose mood prompt. |
|
||||
| 0.00 | Plain T2A — reference ignored. |
|
||||
|
||||
Rule of thumb by intent:
|
||||
* "Fix one part of this clip" -> 0.75 .. 0.85
|
||||
* "Same notes, different instrument" -> 0.55 .. 0.65
|
||||
* "Same chord progression, new content" -> 0.40 .. 0.55
|
||||
* "Use this as a loose mood prompt" -> 0.20 .. 0.35
|
||||
|
||||
If the reference timbre is bleeding through more than you want,
|
||||
lower it; if the structure is gone, raise it.
|
||||
|
||||
Prerequisites: same as `basic_stable_audio.py`.
|
||||
"""
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
PROMPT = "Change the piano to a cello playing the same notes"
|
||||
# Path to any audio-bearing file (wav, mp3, mp4, m4a, flac, ...).
|
||||
# Set to `None` to skip A2A and run plain T2A.
|
||||
INIT_AUDIO_PATH: str | None = None
|
||||
# Reference fidelity in [0, 1] -- higher = closer to source.
|
||||
INIT_AUDIO_STRENGTH = 0.6
|
||||
|
||||
|
||||
def main() -> None:
|
||||
generator = VideoGenerator.from_pretrained(
|
||||
"FastVideo/stable-audio-open-1.0-Diffusers",
|
||||
num_gpus=1,
|
||||
)
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
output_path="outputs_audio/stable_audio_a2a/output_a2a.wav",
|
||||
save_video=True,
|
||||
audio_end_in_s=6.0,
|
||||
init_audio=INIT_AUDIO_PATH,
|
||||
init_audio_strength=INIT_AUDIO_STRENGTH,
|
||||
)
|
||||
generator.shutdown()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,84 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
"""Stable Audio Open 1.0 — inpainting / outpainting (loop extension) example.
|
||||
|
||||
User story (loop extension — the killer app):
|
||||
"I have a 6-second drum loop my client likes. They want it as
|
||||
background bed for a 30-second ad. I need it to loop seamlessly,
|
||||
but a hard cut every 6s sounds bad. Let me extend it to 30s,
|
||||
keeping the first 6s exactly as-is and letting the model continue
|
||||
the groove for the remaining 24s."
|
||||
|
||||
User story (audio repair):
|
||||
"There's a microphone bump at 0:14 in this 30-second field
|
||||
recording — really obvious in headphones. Mask out 0:13 to 0:15
|
||||
and let the model regenerate plausible ambience that blends in.
|
||||
Everything else stays exactly as I recorded it."
|
||||
|
||||
User story (transition smoothing):
|
||||
"I have two 10-second clips I want to crossfade. Mask out a 1s
|
||||
overlap region in the middle and let the model invent a coherent
|
||||
transition between the two."
|
||||
|
||||
How it works (RePaint-style blending):
|
||||
Stable Audio Open 1.0 wasn't trained as an inpainting model
|
||||
(`model_type=diffusion_cond`, not `diffusion_cond_inpaint`), so we
|
||||
can't use the upstream's mask-conditioned approach directly. We
|
||||
use the RePaint trick instead, which works on any v-prediction
|
||||
diffusion model:
|
||||
|
||||
1. Encode the reference clip into latent space.
|
||||
2. At every denoising step `i`, replace the kept region of the
|
||||
in-flight latent (where mask == 1) with the reference
|
||||
re-noised to the next timestep's sigma. Only the unkept
|
||||
region (mask == 0) is freely denoised.
|
||||
3. After the loop, the kept region is exactly the reference;
|
||||
the unkept region is freshly generated content.
|
||||
|
||||
This is approximate compared to a properly trained inpainting
|
||||
checkpoint — the seam between kept/unkept can have slight EQ
|
||||
discontinuity — but it works on the existing public model.
|
||||
|
||||
Tunable: the mask is a 1-D tensor in {0, 1} at the model's sample
|
||||
rate. Conventions:
|
||||
1.0 = keep this sample from the reference
|
||||
0.0 = regenerate this sample
|
||||
|
||||
Prerequisites: same as `basic_stable_audio.py`.
|
||||
"""
|
||||
import os
|
||||
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
PROMPT = "Steady lo-fi hip hop drum loop with vinyl crackle."
|
||||
# Required: path to the reference audio file (wav, mp3, mp4, m4a, flac,
|
||||
# ...) you want to extend or repair. The pipeline raises if a mask is
|
||||
# passed without a reference, so this must be a real path.
|
||||
REFERENCE_AUDIO_PATH = "path/to/your/loop.wav"
|
||||
KEEP_SECONDS = 6.0 # first KEEP_SECONDS preserved exactly
|
||||
TOTAL_SECONDS = 12.0 # extend the loop to this duration
|
||||
|
||||
|
||||
def main() -> None:
|
||||
if not os.path.isfile(REFERENCE_AUDIO_PATH):
|
||||
raise FileNotFoundError(
|
||||
f"REFERENCE_AUDIO_PATH={REFERENCE_AUDIO_PATH!r} does not exist. "
|
||||
"Edit this script to point at a real audio file (wav/mp3/mp4/"
|
||||
"m4a/flac) before running.")
|
||||
generator = VideoGenerator.from_pretrained(
|
||||
"FastVideo/stable-audio-open-1.0-Diffusers",
|
||||
num_gpus=1,
|
||||
)
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
output_path="outputs_audio/stable_audio_inpaint/output_inpaint.wav",
|
||||
save_video=True,
|
||||
audio_end_in_s=TOTAL_SECONDS,
|
||||
inpaint_audio=REFERENCE_AUDIO_PATH,
|
||||
# Tuple form: keep first KEEP_SECONDS, regenerate the rest.
|
||||
inpaint_mask=(KEEP_SECONDS, TOTAL_SECONDS),
|
||||
)
|
||||
generator.shutdown()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,53 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
"""Stable Audio Open Small — fast / lightweight T2A example.
|
||||
|
||||
User story (interactive UI builder):
|
||||
"I'm building a sound-design UI where the user types a prompt and
|
||||
we want sub-2-second feedback so the experience feels like
|
||||
autocomplete, not a render queue. The full Stable Audio Open 1.0
|
||||
takes ~8s on a single GPU; the small variant takes a fraction of
|
||||
that — quality is lower but completely usable for real-time
|
||||
iteration."
|
||||
|
||||
User story (overnight batch jobs):
|
||||
"I'm generating 10,000 short SFX variants for a procedural game.
|
||||
Wall-clock matters more than per-clip polish — give me the small
|
||||
model so I can fit the run in one night instead of a week."
|
||||
|
||||
How it works:
|
||||
The small variant is a separate Stability AI checkpoint
|
||||
(`stabilityai/stable-audio-open-small`) that ships the same Oobleck
|
||||
VAE as the 1.0 base model but a smaller / faster DiT (`embed_dim=1024`,
|
||||
`depth=16`, `qk_norm="ln"`) and only one duration conditioner
|
||||
(`seconds_total`, no `seconds_start`). FastVideo loads from the
|
||||
converted Diffusers-format repo `FastVideo/stable-audio-open-small-Diffusers`
|
||||
via the standard component loader; per-variant arch fields come
|
||||
from `transformer/config.json` and `conditioner/config.json`.
|
||||
|
||||
Prerequisites: same as `basic_stable_audio.py`. The converted repo is
|
||||
public so no gated-access flow is required.
|
||||
"""
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
PROMPT = "Lo-fi hip hop instrumental with vinyl crackle and gentle piano."
|
||||
|
||||
|
||||
def main() -> None:
|
||||
generator = VideoGenerator.from_pretrained(
|
||||
"FastVideo/stable-audio-open-small-Diffusers",
|
||||
num_gpus=1,
|
||||
)
|
||||
output_path = "outputs_audio/stable_audio_small/output_stable_audio_small.wav"
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
output_path=output_path,
|
||||
save_video=True,
|
||||
# Small variant trains on a ~11.9s window — keep `audio_end_in_s`
|
||||
# at or below that.
|
||||
audio_end_in_s=6.0,
|
||||
)
|
||||
generator.shutdown()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_wan2_2_14B_t2v"
|
||||
def main():
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_wan2_1_Fun"
|
||||
OUTPUT_NAME = "wan2.1_test"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
# from fastvideo.api.sampling_param import SamplingParam
|
||||
# from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "video_samples_wan2_2_14B_i2v"
|
||||
def main():
|
||||
|
||||
@@ -1,100 +0,0 @@
|
||||
"""Generate one LTX2 video and score it with VBench metrics.
|
||||
|
||||
The generation block is the same as
|
||||
``examples/inference/basic/basic_ltx2.py`` — same prompt, same model,
|
||||
same shape, same num_frames. After ``shutdown()`` the script loads the
|
||||
mp4 back, builds a single :class:`fastvideo.eval.Evaluator`, and runs
|
||||
the prompt-aware VBench subset that's meaningful for an arbitrary
|
||||
text→video sample.
|
||||
|
||||
The first run downloads CLIP / DINO / RAFT / AMT / ViCLIP / MUSIQ
|
||||
weights to ``~/.cache/fastvideo/eval/`` (~few GB total).
|
||||
|
||||
GPU memory caveat
|
||||
-----------------
|
||||
Scoring 1088×1920×121 with all 8 metrics needs a dedicated GPU (~80 GB).
|
||||
On a shared GPU, ``vbench.motion_smoothness`` (AMT correlation volume)
|
||||
will OOM — its memory autoscale reads ``total_memory`` rather than
|
||||
``mem_get_info()`` free memory and therefore underestimates the
|
||||
required scale-down. Drop ``motion_smoothness`` from ``METRICS`` if
|
||||
sharing, or run on a smaller-resolution generation.
|
||||
"""
|
||||
import torch
|
||||
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.eval import Evaluator
|
||||
from fastvideo.eval.io import build_eval_kwargs
|
||||
|
||||
PROMPT = (
|
||||
"A warm sunny backyard. The camera starts in a tight cinematic close-up "
|
||||
"of a woman and a man in their 30s, facing each other with serious "
|
||||
"expressions. The woman, emotional and dramatic, says softly, \"That's "
|
||||
"it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
|
||||
"annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
|
||||
"then mutters defensively, \"He's just having fun.\" The camera slowly "
|
||||
"pans right, revealing the grandfather in the garden wearing enormous "
|
||||
"butterfly wings, waving his arms in the air like he's trying to take "
|
||||
"off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
|
||||
"The woman covers her face, on the verge of tears. The tone is deadpan, "
|
||||
"absurd, and quietly tragic."
|
||||
)
|
||||
|
||||
# VBench sub-metrics meaningful for an arbitrary text→video sample
|
||||
# (just the generated frames, optionally fps + the source prompt).
|
||||
# Structured-prompt metrics (vbench.color, vbench.multiple_objects,
|
||||
# vbench.scene, ...) are excluded — they need prompts built to a
|
||||
# specific schema.
|
||||
METRICS = [
|
||||
"vbench.aesthetic_quality", # CLIP + LAION aesthetic head
|
||||
"vbench.subject_consistency", # DINO frame-to-first cosine
|
||||
"vbench.background_consistency", # DINO on background patches
|
||||
"vbench.imaging_quality", # pyiqa MUSIQ
|
||||
"vbench.temporal_flickering", # pixel-wise frame deltas
|
||||
"vbench.motion_smoothness", # AMT frame interpolator residual
|
||||
"vbench.dynamic_degree", # RAFT optical-flow magnitude (needs fps)
|
||||
"vbench.overall_consistency", # ViCLIP video↔prompt similarity
|
||||
]
|
||||
|
||||
|
||||
def main() -> None:
|
||||
# ----- generation (matches examples/inference/basic/basic_ltx2.py) -----
|
||||
generator = VideoGenerator.from_pretrained(
|
||||
"Davids048/LTX2-Base-Diffusers",
|
||||
num_gpus=1,
|
||||
)
|
||||
|
||||
output_path = "outputs_video/ltx2_basic/output_ltx2_base_t2v_1088_1920_1.1.mp4"
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
output_path=output_path,
|
||||
save_video=True,
|
||||
num_frames=121,
|
||||
height=1088,
|
||||
width=1920,
|
||||
)
|
||||
generator.shutdown()
|
||||
# Free residual CUDA memory the generator left behind so the
|
||||
# evaluator can grab the largest possible workspace for AMT/RAFT.
|
||||
torch.cuda.empty_cache()
|
||||
|
||||
# ----- scoring -----
|
||||
print(f"\n[eval] building evaluator: {METRICS}")
|
||||
evaluator = Evaluator(metrics=METRICS)
|
||||
|
||||
# LTX2 outputs at 24 fps by default.
|
||||
sample = build_eval_kwargs({"prompt": PROMPT}, output_path, fps=24.0)
|
||||
print(f"[eval] running ({sample['video'].shape[1]} frames @ 24 fps)...")
|
||||
results = evaluator.evaluate(**sample)
|
||||
|
||||
print("\n=== VBench scores ===")
|
||||
for name in METRICS:
|
||||
r = results[name]
|
||||
if r.score is None:
|
||||
reason = r.details.get("skipped", "no score")
|
||||
print(f" {name}: SKIPPED ({reason})")
|
||||
else:
|
||||
print(f" {name}: {r.score:.4f}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,157 +0,0 @@
|
||||
"""End-to-end Physics-IQ: dataset → generate → score → aggregate.
|
||||
|
||||
Generates one video per take-1 scenario with LTX2 (using the scenario
|
||||
caption as the prompt), scores each generated video against the take-1
|
||||
reference and the take-2 "physical-variance" reference, and prints
|
||||
aggregate scores using :meth:`PhysicsIQMetric.aggregate_components` —
|
||||
the official scoring recipe from the upstream benchmark.
|
||||
|
||||
Reference videos / masks / switch-frames auto-fetch on first miss into
|
||||
``${FASTVIDEO_EVAL_CACHE}/datasets/physics_iq/``; pass ``--dataset-root``
|
||||
to point at a pre-downloaded mirror instead.
|
||||
|
||||
Quick smoke run on 4 scenarios across 2 GPUs::
|
||||
|
||||
python examples/inference/eval/bench_physics_iq.py \\
|
||||
--limit 4 --num-gpus 2 \\
|
||||
--videos-dir outputs_video/physics_iq_smoke
|
||||
|
||||
Re-score existing generations without regenerating::
|
||||
|
||||
python examples/inference/eval/bench_physics_iq.py \\
|
||||
--videos-dir outputs_video/physics_iq_smoke \\
|
||||
--skip-generation
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from fastvideo.eval import create_evaluator, get_metric
|
||||
from fastvideo.eval.datasets import get_dataset
|
||||
|
||||
|
||||
def _expected_filename(row: dict) -> str:
|
||||
"""Filename Physics-IQ expects for the generated video for *row*.
|
||||
|
||||
Uses the dataset's own ``expected_gen_filename`` annotation so the
|
||||
output filenames match the benchmark's manifest convention.
|
||||
"""
|
||||
return row["auxiliary_info"]["expected_gen_filename"]
|
||||
|
||||
|
||||
def _generate_videos(rows: list[dict], videos_dir: Path,
|
||||
model: str, num_gpus: int,
|
||||
num_frames: int, height: int, width: int) -> None:
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
videos_dir.mkdir(parents=True, exist_ok=True)
|
||||
todo = [(row, videos_dir / _expected_filename(row)) for row in rows]
|
||||
todo = [(row, out) for (row, out) in todo if not out.is_file()]
|
||||
if not todo:
|
||||
print(f"[gen] all {len(rows)} videos already present; skipping.")
|
||||
return
|
||||
|
||||
print(f"[gen] {len(todo)}/{len(rows)} scenarios to render with {model} "
|
||||
f"({num_frames}x{height}x{width})...")
|
||||
gen = VideoGenerator.from_pretrained(model, num_gpus=num_gpus)
|
||||
try:
|
||||
for row, out_path in todo:
|
||||
gen.generate_video(
|
||||
prompt=row["prompt"], output_path=str(out_path), save_video=True,
|
||||
num_frames=num_frames, height=height, width=width,
|
||||
)
|
||||
finally:
|
||||
gen.shutdown()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
p = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--dataset-root", type=Path, default=None,
|
||||
help="Path to a pre-downloaded Physics-IQ release. "
|
||||
"Defaults to ${FASTVIDEO_EVAL_CACHE}/datasets/physics_iq, "
|
||||
"auto-fetching missing assets from the public bucket.")
|
||||
p.add_argument("--videos-dir", type=Path,
|
||||
default=Path("outputs_video/bench_physics_iq"),
|
||||
help="Where to read/write generated videos.")
|
||||
p.add_argument("--limit", type=int, default=None,
|
||||
help="Truncate to first N scenarios for smoke runs.")
|
||||
p.add_argument("--num-gpus", type=int, default=1)
|
||||
p.add_argument("--model", default="Davids048/LTX2-Base-Diffusers",
|
||||
help="HF repo id of the text→video generator to use.")
|
||||
p.add_argument("--num-frames", type=int, default=121)
|
||||
p.add_argument("--height", type=int, default=1088)
|
||||
p.add_argument("--width", type=int, default=1920)
|
||||
p.add_argument("--skip-generation", action="store_true",
|
||||
help="Re-score existing videos under --videos-dir.")
|
||||
p.add_argument("--scores-out", type=Path, default=None,
|
||||
help="Where to write per-scenario scores (JSON). "
|
||||
"Defaults to <videos-dir>/scores.json.")
|
||||
args = p.parse_args()
|
||||
|
||||
# 1. Walk the Physics-IQ corpus. Pass --limit to the dataset
|
||||
# constructor so auto-download only fetches the assets we'll use.
|
||||
ds = get_dataset("physics_iq", dataset_root=args.dataset_root, limit=args.limit)
|
||||
rows = list(ds)
|
||||
print(f"[load] Physics-IQ: {len(rows)} scenarios from {ds.dataset_dir}")
|
||||
|
||||
# 2. Generate (or reuse) one mp4 per scenario.
|
||||
if not args.skip_generation:
|
||||
_generate_videos(
|
||||
rows, args.videos_dir, args.model, args.num_gpus,
|
||||
args.num_frames, args.height, args.width,
|
||||
)
|
||||
|
||||
# 3. Score each scenario. The metric reads file paths directly out
|
||||
# of the row dict (reference, reference_take2, masks), so we
|
||||
# just attach the generated video path and forward.
|
||||
evaluator = create_evaluator(metrics=["physics_iq"], num_gpus=args.num_gpus)
|
||||
|
||||
samples: list[dict] = []
|
||||
matched: list[dict] = []
|
||||
for row in rows:
|
||||
video_path = args.videos_dir / _expected_filename(row)
|
||||
if not video_path.is_file():
|
||||
print(f"[eval] missing {video_path}; skipping.")
|
||||
continue
|
||||
# The physics_iq metric accepts file paths via its polymorphic
|
||||
# input handling — no need to load the tensors here.
|
||||
samples.append({"video": str(video_path), **row})
|
||||
matched.append(row)
|
||||
|
||||
all_results = evaluator.evaluate(samples=samples)
|
||||
evaluator.shutdown()
|
||||
|
||||
# 4. Aggregate per the upstream scoring recipe.
|
||||
metric = get_metric("physics_iq")
|
||||
components = metric.aggregate_components(
|
||||
[r["physics_iq"] for r in all_results]
|
||||
)
|
||||
|
||||
print()
|
||||
print("=== Physics-IQ aggregate ===")
|
||||
for name, value in components.items():
|
||||
print(f" {name:24s} {value:.4f}")
|
||||
|
||||
detailed = [
|
||||
{
|
||||
"scenario": row["auxiliary_info"]["scenario_id"],
|
||||
"view": row["view"],
|
||||
"scenario_name": row["auxiliary_info"]["scenario_name"],
|
||||
"score": results["physics_iq"].score,
|
||||
}
|
||||
for row, results in zip(matched, all_results)
|
||||
]
|
||||
out = args.scores_out or (args.videos_dir / "scores.json")
|
||||
out.parent.mkdir(parents=True, exist_ok=True)
|
||||
out.write_text(json.dumps(
|
||||
{"aggregate": components, "per_scenario": detailed},
|
||||
indent=2,
|
||||
))
|
||||
print(f"\n[done] per-scenario scores → {out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,155 +0,0 @@
|
||||
"""End-to-end VBench: dataset → generate → score → aggregate.
|
||||
|
||||
Iterates the VBench prompt corpus, generates one video per prompt with
|
||||
LTX2, scores each generated video against the requested ``vbench.*``
|
||||
sub-metrics, and prints per-metric averages over the run.
|
||||
|
||||
Re-running with ``--skip-generation`` reuses any mp4 already on disk
|
||||
under ``--videos-dir``, so you can iterate on metric selection without
|
||||
re-paying the generation cost.
|
||||
|
||||
Example — quick smoke run on 4 prompts from the ``aesthetic_quality``
|
||||
dimension across 2 GPUs::
|
||||
|
||||
python examples/inference/eval/bench_vbench.py \\
|
||||
--dimensions aesthetic_quality \\
|
||||
--limit 4 --num-gpus 2 \\
|
||||
--videos-dir outputs_video/vbench_smoke
|
||||
|
||||
Full benchmark on a single dimension::
|
||||
|
||||
python examples/inference/eval/bench_vbench.py \\
|
||||
--dimensions subject_consistency --num-gpus 8
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
|
||||
from fastvideo.eval import create_evaluator
|
||||
from fastvideo.eval.datasets import get_dataset
|
||||
|
||||
|
||||
def _slugify(prompt: str, max_len: int = 100) -> str:
|
||||
"""Filesystem-safe filename stem; mirrors VBench's official convention."""
|
||||
s = re.sub(r'[\\/:*?"<>|]', "", prompt[:max_len]).strip().strip(".")
|
||||
return re.sub(r"\s+", " ", s) or "output"
|
||||
|
||||
|
||||
def _generate_videos(prompts: list[str], videos_dir: Path,
|
||||
model: str, num_gpus: int,
|
||||
num_frames: int, height: int, width: int) -> None:
|
||||
from fastvideo import VideoGenerator
|
||||
|
||||
videos_dir.mkdir(parents=True, exist_ok=True)
|
||||
todo = [(p, videos_dir / f"{_slugify(p)}.mp4") for p in prompts]
|
||||
todo = [(p, out) for (p, out) in todo if not out.is_file()]
|
||||
if not todo:
|
||||
print(f"[gen] all {len(prompts)} videos already present; skipping.")
|
||||
return
|
||||
|
||||
print(f"[gen] {len(todo)}/{len(prompts)} prompts to render with {model} "
|
||||
f"({num_frames}x{height}x{width})...")
|
||||
gen = VideoGenerator.from_pretrained(model, num_gpus=num_gpus)
|
||||
try:
|
||||
for prompt, out_path in todo:
|
||||
gen.generate_video(
|
||||
prompt=prompt, output_path=str(out_path), save_video=True,
|
||||
num_frames=num_frames, height=height, width=width,
|
||||
)
|
||||
finally:
|
||||
gen.shutdown()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
p = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--dimensions", default="aesthetic_quality,subject_consistency",
|
||||
help="Comma-separated VBench dimensions (or 'all').")
|
||||
p.add_argument("--limit", type=int, default=None,
|
||||
help="Truncate to first N prompts for smoke runs.")
|
||||
p.add_argument("--videos-dir", type=Path,
|
||||
default=Path("outputs_video/bench_vbench"))
|
||||
p.add_argument("--num-gpus", type=int, default=1)
|
||||
p.add_argument("--model", default="Davids048/LTX2-Base-Diffusers",
|
||||
help="HF repo id of the text→video generator to use.")
|
||||
p.add_argument("--num-frames", type=int, default=121)
|
||||
p.add_argument("--height", type=int, default=1088)
|
||||
p.add_argument("--width", type=int, default=1920)
|
||||
p.add_argument("--fps", type=float, default=24.0,
|
||||
help="Frame-rate annotation passed to fps-aware metrics.")
|
||||
p.add_argument("--skip-generation", action="store_true",
|
||||
help="Re-score existing videos under --videos-dir without "
|
||||
"regenerating.")
|
||||
p.add_argument("--scores-out", type=Path, default=None,
|
||||
help="Where to dump per-prompt scores as JSON. "
|
||||
"Defaults to <videos-dir>/scores.json.")
|
||||
args = p.parse_args()
|
||||
|
||||
# 1. Pull prompts from VBench.
|
||||
dims_arg: list[str] | str = (
|
||||
args.dimensions if args.dimensions == "all"
|
||||
else [d.strip() for d in args.dimensions.split(",") if d.strip()]
|
||||
)
|
||||
ds = get_dataset("vbench", dimensions=dims_arg)
|
||||
rows = list(ds)[: args.limit]
|
||||
print(f"[load] VBench: {len(rows)} prompts across {ds.dimensions}")
|
||||
|
||||
# 2. Generate (or reuse) one mp4 per prompt.
|
||||
if not args.skip_generation:
|
||||
_generate_videos(
|
||||
[row["prompt"] for row in rows],
|
||||
args.videos_dir, args.model, args.num_gpus,
|
||||
args.num_frames, args.height, args.width,
|
||||
)
|
||||
|
||||
# 3. Score each video against the requested vbench sub-metrics.
|
||||
metric_names = sorted(set(f"vbench.{d}" for d in ds.dimensions))
|
||||
print(f"[eval] metrics: {metric_names}")
|
||||
evaluator = create_evaluator(metrics=metric_names, num_gpus=args.num_gpus)
|
||||
|
||||
samples: list[dict] = []
|
||||
matched_rows: list[dict] = []
|
||||
for row in rows:
|
||||
video_path = args.videos_dir / f"{_slugify(row['prompt'])}.mp4"
|
||||
if not video_path.is_file():
|
||||
print(f"[eval] missing {video_path}; skipping this row.")
|
||||
continue
|
||||
# Pass the path; the worker decodes lazily so memory stays bounded.
|
||||
samples.append({
|
||||
"video": str(video_path),
|
||||
"fps": args.fps,
|
||||
**row, # prompt / aux / dims
|
||||
})
|
||||
matched_rows.append(row)
|
||||
|
||||
all_results = evaluator.evaluate(samples=samples)
|
||||
evaluator.shutdown()
|
||||
|
||||
# 4. Aggregate per-metric.
|
||||
by_metric: dict[str, list[float]] = defaultdict(list)
|
||||
detailed: list[dict] = []
|
||||
for row, results in zip(matched_rows, all_results):
|
||||
scores = {name: r.score for name, r in results.items()}
|
||||
detailed.append({"prompt": row["prompt"], "scores": scores})
|
||||
for name, score in scores.items():
|
||||
if score is not None:
|
||||
by_metric[name].append(score)
|
||||
|
||||
print()
|
||||
print("=== per-metric averages ===")
|
||||
for name in sorted(by_metric):
|
||||
avg = sum(by_metric[name]) / len(by_metric[name])
|
||||
print(f" {name:42s} {avg:.4f} (n={len(by_metric[name])})")
|
||||
|
||||
out = args.scores_out or (args.videos_dir / "scores.json")
|
||||
out.parent.mkdir(parents=True, exist_ok=True)
|
||||
out.write_text(json.dumps(detailed, indent=2))
|
||||
print(f"\n[done] per-prompt scores → {out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,167 +0,0 @@
|
||||
"""End-to-end: generate a video with LTX2 and score it with VBench.
|
||||
|
||||
Pipeline:
|
||||
prompt → LTX2-Base → mp4 → fastvideo.eval → vbench scores
|
||||
|
||||
Run::
|
||||
|
||||
pip install -e .[eval]
|
||||
git submodule update --init fastvideo/third_party/eval/vbench
|
||||
|
||||
python examples/inference/eval/eval_ltx2_vbench.py
|
||||
# or with 4 GPUs and the distilled checkpoint:
|
||||
python examples/inference/eval/eval_ltx2_vbench.py \
|
||||
--model FastVideo/LTX2-Distilled-Diffusers --num-gpus 4
|
||||
|
||||
The default metric set covers the vbench sub-metrics that are
|
||||
meaningful for an arbitrary text→video sample — i.e. those that need
|
||||
only the generated video (and optionally fps + the source prompt).
|
||||
Structured-prompt metrics like ``vbench.color``, ``vbench.scene``,
|
||||
``vbench.multiple_objects`` etc. are *not* on by default — they only
|
||||
make sense when the prompt is built to a specific schema, and they
|
||||
require GRiT/detectron2 setup. Pass them via ``--metrics`` if you have
|
||||
a matching prompt.
|
||||
|
||||
First-time runs download CLIP, DINO, RAFT, AMT, ViCLIP, and MUSIQ
|
||||
weights to ``~/.cache/fastvideo/eval/models/`` and
|
||||
``~/.cache/torch/hub/`` (~few GB total). Subsequent runs are fast.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.eval import create_evaluator
|
||||
from fastvideo.eval.io import load_video
|
||||
|
||||
|
||||
PROMPT = (
|
||||
"A warm sunny backyard. The camera starts in a tight cinematic close-up "
|
||||
"of a woman and a man in their 30s, facing each other with serious "
|
||||
"expressions. The woman, emotional and dramatic, says softly, \"That's "
|
||||
"it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
|
||||
"annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
|
||||
"then mutters defensively, \"He's just having fun.\" The camera slowly "
|
||||
"pans right, revealing the grandfather in the garden wearing enormous "
|
||||
"butterfly wings, waving his arms in the air like he's trying to take "
|
||||
"off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
|
||||
"The woman covers her face, on the verge of tears. The tone is deadpan, "
|
||||
"absurd, and quietly tragic."
|
||||
)
|
||||
|
||||
DEFAULT_METRICS = [
|
||||
# No-input metrics: just need the generated frames.
|
||||
"vbench.aesthetic_quality", # CLIP + LAION aesthetic head
|
||||
"vbench.subject_consistency", # DINO frame-to-first cosine
|
||||
"vbench.background_consistency", # DINO on background patches
|
||||
"vbench.imaging_quality", # pyiqa MUSIQ
|
||||
"vbench.temporal_flickering", # pixel-wise frame deltas
|
||||
"vbench.motion_smoothness", # AMT frame interpolator residual
|
||||
# Need fps annotation:
|
||||
"vbench.dynamic_degree", # RAFT optical-flow magnitude
|
||||
# Need the source prompt:
|
||||
"vbench.overall_consistency", # ViCLIP video↔prompt similarity
|
||||
]
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
p = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--model", default="Davids048/LTX2-Base-Diffusers",
|
||||
help="HF repo id of the LTX2 checkpoint.")
|
||||
p.add_argument("--num-gpus", type=int, default=1)
|
||||
p.add_argument("--output", default="outputs_video/ltx2_eval/clip.mp4",
|
||||
help="Where to save the generated mp4.")
|
||||
p.add_argument("--num-frames", type=int, default=121)
|
||||
p.add_argument("--height", type=int, default=1088)
|
||||
p.add_argument("--width", type=int, default=1920)
|
||||
p.add_argument("--prompt", default=PROMPT)
|
||||
p.add_argument("--fps", type=float, default=24.0,
|
||||
help="Frame-rate annotation passed to fps-aware metrics "
|
||||
"(e.g. vbench.dynamic_degree). LTX2 outputs at 24 fps "
|
||||
"by default.")
|
||||
p.add_argument("--metrics", default=",".join(DEFAULT_METRICS),
|
||||
help="Comma-separated metric names. Pass 'all' for every "
|
||||
"registered metric, or e.g. 'vbench' for the whole group.")
|
||||
p.add_argument("--scores-out", default="outputs_video/ltx2_eval/scores.json")
|
||||
p.add_argument("--skip-generation", action="store_true",
|
||||
help="Reuse an existing --output video instead of regenerating.")
|
||||
return p.parse_args()
|
||||
|
||||
|
||||
def generate(args: argparse.Namespace) -> Path:
|
||||
out = Path(args.output)
|
||||
if args.skip_generation and out.is_file():
|
||||
print(f"[gen] reusing existing video at {out}")
|
||||
return out
|
||||
out.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
print(f"[gen] loading {args.model} ({args.num_gpus} GPU)...")
|
||||
generator = VideoGenerator.from_pretrained(args.model, num_gpus=args.num_gpus)
|
||||
try:
|
||||
print(f"[gen] generating to {out}...")
|
||||
generator.generate_video(
|
||||
prompt=args.prompt,
|
||||
output_path=str(out),
|
||||
save_video=True,
|
||||
num_frames=args.num_frames,
|
||||
height=args.height,
|
||||
width=args.width,
|
||||
)
|
||||
finally:
|
||||
generator.shutdown()
|
||||
return out
|
||||
|
||||
|
||||
def evaluate_video(video_path: Path, prompt: str, fps: float,
|
||||
metric_names) -> dict:
|
||||
print(f"[eval] loading video from {video_path}...")
|
||||
video = load_video(str(video_path)) # (T, C, H, W) in [0, 1]
|
||||
video = video.unsqueeze(0) # → (1, T, C, H, W)
|
||||
|
||||
print(f"[eval] building evaluator: {metric_names}")
|
||||
evaluator = create_evaluator(metrics=metric_names, device="cuda")
|
||||
|
||||
print(f"[eval] running ({video.shape[1]} frames @ {fps} fps)...")
|
||||
results = evaluator.evaluate(
|
||||
video=video,
|
||||
text_prompt=[prompt],
|
||||
fps=fps,
|
||||
)
|
||||
|
||||
if isinstance(results, list):
|
||||
results = results[0] # batch of 1
|
||||
|
||||
return {
|
||||
name: {"score": r.score, "details": r.details}
|
||||
for name, r in results.items()
|
||||
}
|
||||
|
||||
|
||||
def main() -> None:
|
||||
args = parse_args()
|
||||
if args.metrics.strip() == "all":
|
||||
metric_names = "all"
|
||||
else:
|
||||
metric_names = [m.strip() for m in args.metrics.split(",") if m.strip()]
|
||||
|
||||
video_path = generate(args)
|
||||
scores = evaluate_video(video_path, args.prompt, args.fps, metric_names)
|
||||
|
||||
print("\n=== VBench scores ===")
|
||||
for name, payload in scores.items():
|
||||
print(f" {name}: {payload['score']}")
|
||||
|
||||
out = Path(args.scores_out)
|
||||
out.parent.mkdir(parents=True, exist_ok=True)
|
||||
out.write_text(json.dumps(
|
||||
{"video": str(video_path), "prompt": args.prompt, "scores": scores},
|
||||
indent=2,
|
||||
))
|
||||
print(f"[done] scores written to {out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,95 +0,0 @@
|
||||
"""Score a folder of videos in parallel across multiple GPUs.
|
||||
|
||||
Uses :meth:`Evaluator.evaluate(samples=[...])`, which round-robins each
|
||||
sample dict across the GPU replicas the evaluator was built with.
|
||||
|
||||
Example::
|
||||
|
||||
python examples/inference/eval/score_folder.py \\
|
||||
--videos generated/ \\
|
||||
--metrics vbench.aesthetic_quality,vbench.subject_consistency \\
|
||||
--num-gpus 4 \\
|
||||
--output scores.json
|
||||
|
||||
Pair each generated video with a same-name reference video (e.g.
|
||||
``ref/<stem>.mp4``) by passing ``--reference-dir``::
|
||||
|
||||
python examples/inference/eval/score_folder.py \\
|
||||
--videos generated/ --reference-dir ref/ \\
|
||||
--metrics common.psnr,common.ssim,common.lpips \\
|
||||
--num-gpus 4
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from fastvideo.eval import create_evaluator
|
||||
|
||||
|
||||
def _list_videos(directory: Path) -> list[Path]:
|
||||
exts = {".mp4", ".avi", ".mov", ".mkv", ".gif"}
|
||||
return sorted(p for p in directory.iterdir() if p.suffix.lower() in exts)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
p = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--videos", type=Path, required=True,
|
||||
help="Directory of generated videos.")
|
||||
p.add_argument("--reference-dir", type=Path, default=None,
|
||||
help="Directory of reference videos with matching stems.")
|
||||
p.add_argument("--metrics", default="vbench.aesthetic_quality")
|
||||
p.add_argument("--num-gpus", type=int, default=1)
|
||||
p.add_argument("--fps", type=float, default=None,
|
||||
help="Frame-rate annotation for fps-aware metrics.")
|
||||
p.add_argument("--output", type=Path, default=Path("scores.json"))
|
||||
args = p.parse_args()
|
||||
|
||||
video_paths = _list_videos(args.videos)
|
||||
if not video_paths:
|
||||
raise SystemExit(f"No videos under {args.videos}")
|
||||
print(f"Found {len(video_paths)} videos in {args.videos}")
|
||||
|
||||
metrics: list[str] | str = (
|
||||
args.metrics if args.metrics == "all"
|
||||
else [m.strip() for m in args.metrics.split(",") if m.strip()]
|
||||
)
|
||||
evaluator = create_evaluator(metrics=metrics, num_gpus=args.num_gpus)
|
||||
|
||||
# Build per-video sample dicts holding *paths*, not pre-loaded
|
||||
# tensors. Each path is decoded inside the worker thread that picks
|
||||
# up its sample, so peak resident memory is bounded by num_gpus
|
||||
# rather than scaling with the size of the folder.
|
||||
samples: list[dict] = []
|
||||
for vp in video_paths:
|
||||
sample: dict = {"video": str(vp)}
|
||||
if args.reference_dir is not None:
|
||||
ref_path = args.reference_dir / vp.name
|
||||
if not ref_path.is_file():
|
||||
raise FileNotFoundError(f"Missing reference for {vp.name} at {ref_path}")
|
||||
sample["reference"] = str(ref_path)
|
||||
if args.fps is not None:
|
||||
sample["fps"] = args.fps
|
||||
samples.append(sample)
|
||||
|
||||
print(f"Scoring with {len(evaluator.metric_names)} metric(s) "
|
||||
f"on {evaluator.num_gpus} GPU(s)...")
|
||||
all_results = evaluator.evaluate(samples=samples)
|
||||
evaluator.shutdown()
|
||||
|
||||
payload = [
|
||||
{
|
||||
"video": str(vp),
|
||||
"scores": {name: r.score for name, r in results.items()},
|
||||
}
|
||||
for vp, results in zip(video_paths, all_results)
|
||||
]
|
||||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||||
args.output.write_text(json.dumps(payload, indent=2))
|
||||
print(f"Wrote {args.output}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,68 +0,0 @@
|
||||
"""Score one video on one GPU.
|
||||
|
||||
Smallest possible use of ``fastvideo.eval``: load an mp4, build an
|
||||
:class:`Evaluator` for the requested metric set, run it.
|
||||
|
||||
Examples::
|
||||
|
||||
# Reference-free (just the generated video):
|
||||
python examples/inference/eval/score_video.py \\
|
||||
--video clip.mp4 \\
|
||||
--metrics vbench.aesthetic_quality,vbench.imaging_quality
|
||||
|
||||
# Reference-paired (compare against ground truth):
|
||||
python examples/inference/eval/score_video.py \\
|
||||
--video gen.mp4 --reference ref.mp4 \\
|
||||
--metrics common.psnr,common.ssim,common.lpips
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
|
||||
from fastvideo.eval import create_evaluator
|
||||
from fastvideo.eval.io import load_video
|
||||
|
||||
|
||||
def main() -> None:
|
||||
p = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--video", required=True, help="Path to the generated mp4.")
|
||||
p.add_argument("--reference", default=None,
|
||||
help="Optional path to a reference mp4 (for paired metrics).")
|
||||
p.add_argument("--metrics", default="common.psnr,common.ssim",
|
||||
help="Comma-separated metric names, or a group name like 'vbench'.")
|
||||
p.add_argument("--device", default="cuda:0")
|
||||
p.add_argument("--text-prompt", default=None,
|
||||
help="Text prompt for prompt-aware metrics "
|
||||
"(vbench.overall_consistency, etc.).")
|
||||
p.add_argument("--fps", type=float, default=None,
|
||||
help="Frame-rate annotation for fps-aware metrics "
|
||||
"(vbench.dynamic_degree, etc.).")
|
||||
args = p.parse_args()
|
||||
|
||||
metrics: list[str] | str = (
|
||||
args.metrics if args.metrics in ("all",)
|
||||
else [m.strip() for m in args.metrics.split(",") if m.strip()]
|
||||
)
|
||||
evaluator = create_evaluator(metrics=metrics, device=args.device)
|
||||
|
||||
sample: dict = {"video": load_video(args.video)}
|
||||
if args.reference is not None:
|
||||
sample["reference"] = load_video(args.reference)
|
||||
if args.text_prompt is not None:
|
||||
sample["text_prompt"] = args.text_prompt
|
||||
if args.fps is not None:
|
||||
sample["fps"] = args.fps
|
||||
|
||||
results = evaluator.evaluate(**sample)
|
||||
evaluator.shutdown()
|
||||
|
||||
print(json.dumps(
|
||||
{name: r.score for name, r in results.items()},
|
||||
indent=2,
|
||||
))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -5,7 +5,7 @@ import time
|
||||
|
||||
import gradio as gr
|
||||
from fastvideo.entrypoints.video_generator import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample.base import SamplingParam
|
||||
from copy import deepcopy
|
||||
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ import tempfile
|
||||
|
||||
import gradio as gr
|
||||
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample.base import SamplingParam
|
||||
|
||||
|
||||
MODEL_PATH_MAPPING = {
|
||||
|
||||
@@ -185,7 +185,7 @@ class BaseModelDeployment:
|
||||
|
||||
def _initialize_generator(self, config: Dict[str, Any]) -> None:
|
||||
from fastvideo.entrypoints.video_generator import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample.base import SamplingParam
|
||||
|
||||
print(f"Initializing model: {self.model_path}")
|
||||
self.generator = VideoGenerator.from_pretrained(
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "./lora_out"
|
||||
def main():
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
Inference using a LoRA checkpoint from FastVideo trainer.
|
||||
"""
|
||||
from fastvideo import VideoGenerator
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
|
||||
OUTPUT_PATH = "./lora_out"
|
||||
def main():
|
||||
|
||||
@@ -1,73 +0,0 @@
|
||||
# Cosmos Predict2 2B T2V finetune config.
|
||||
#
|
||||
# Data must be preprocessed with Cosmos VAE + T5 text encoder
|
||||
# into parquet format before training.
|
||||
|
||||
models:
|
||||
student:
|
||||
_target_: fastvideo.train.models.cosmos.CosmosModel
|
||||
init_from: nvidia/Cosmos-Predict2-2B-Video2World
|
||||
trainable: true
|
||||
|
||||
method:
|
||||
_target_: fastvideo.train.methods.fine_tuning.finetune.FineTuneMethod
|
||||
|
||||
training:
|
||||
distributed:
|
||||
num_gpus: 8
|
||||
sp_size: 1
|
||||
tp_size: 1
|
||||
hsdp_replicate_dim: 8
|
||||
hsdp_shard_dim: 1
|
||||
|
||||
data:
|
||||
data_path: data/cosmos_preprocessed
|
||||
dataloader_num_workers: 4
|
||||
train_batch_size: 1
|
||||
training_cfg_rate: 0.0
|
||||
seed: 1000
|
||||
# Cosmos VAE: 4x temporal, 8x spatial compression.
|
||||
# 93 frames -> 24 latent frames, 480x832 -> 60x104
|
||||
num_latent_t: 24
|
||||
num_height: 480
|
||||
num_width: 832
|
||||
num_frames: 93
|
||||
|
||||
optimizer:
|
||||
learning_rate: 1.0e-5
|
||||
betas: [0.9, 0.999]
|
||||
weight_decay: 0.01
|
||||
lr_scheduler: constant
|
||||
lr_warmup_steps: 0
|
||||
|
||||
loop:
|
||||
max_train_steps: 5000
|
||||
gradient_accumulation_steps: 1
|
||||
|
||||
checkpoint:
|
||||
output_dir: outputs/cosmos_finetune
|
||||
training_state_checkpointing_steps: 500
|
||||
checkpoints_total_limit: 3
|
||||
resume_from_checkpoint: latest
|
||||
|
||||
tracker:
|
||||
project_name: fastvideo_cosmos
|
||||
run_name: cosmos_finetune
|
||||
|
||||
model:
|
||||
enable_gradient_checkpointing_type: full
|
||||
|
||||
callbacks:
|
||||
grad_clip:
|
||||
_target_: fastvideo.train.callbacks.grad_clip.GradNormClipCallback
|
||||
max_grad_norm: 1.0
|
||||
validation:
|
||||
_target_: fastvideo.train.callbacks.validation.ValidationCallback
|
||||
pipeline_target: fastvideo.pipelines.basic.cosmos.cosmos_pipeline.Cosmos2VideoToWorldPipeline
|
||||
dataset_file: data/cosmos_preprocessed/validation_prompts.json
|
||||
every_steps: 100
|
||||
sampling_steps: [50]
|
||||
guidance_scale: 6.0
|
||||
|
||||
pipeline:
|
||||
flow_shift: 1.0
|
||||
@@ -1,79 +0,0 @@
|
||||
# Cosmos-Predict2.5-2B Text-to-World overfitting test config.
|
||||
#
|
||||
# Overfits on a few short videos (480x832, 93 frames) to verify the
|
||||
# Cosmos 2.5 training plugin works end-to-end.
|
||||
#
|
||||
# Preprocess data first:
|
||||
# CUDA_VISIBLE_DEVICES=0 python fastvideo/pipelines/preprocess/preprocess_cosmos25_overfit.py
|
||||
#
|
||||
# Run:
|
||||
# bash examples/train/run.sh examples/train/configs/overfit_cosmos25_t2w.yaml
|
||||
|
||||
models:
|
||||
student:
|
||||
_target_: fastvideo.train.models.cosmos.CosmosModel
|
||||
init_from: KyleShao/Cosmos-Predict2.5-2B-Diffusers
|
||||
trainable: true
|
||||
enable_gradient_checkpointing_type: full
|
||||
flow_shift: 1.0
|
||||
|
||||
method:
|
||||
_target_: fastvideo.train.methods.fine_tuning.finetune.FineTuneMethod
|
||||
|
||||
training:
|
||||
distributed:
|
||||
num_gpus: 1
|
||||
sp_size: 1
|
||||
tp_size: 1
|
||||
hsdp_replicate_dim: 1
|
||||
hsdp_shard_dim: 1
|
||||
|
||||
data:
|
||||
data_path: data/cosmos25_overfit_preprocessed
|
||||
dataloader_num_workers: 0
|
||||
train_batch_size: 1
|
||||
training_cfg_rate: 0.0
|
||||
seed: 42
|
||||
num_latent_t: 24
|
||||
num_height: 480
|
||||
num_width: 832
|
||||
num_frames: 93
|
||||
|
||||
optimizer:
|
||||
learning_rate: 5.0e-5
|
||||
betas: [0.9, 0.999]
|
||||
weight_decay: 0.0
|
||||
lr_scheduler: constant
|
||||
lr_warmup_steps: 0
|
||||
|
||||
loop:
|
||||
max_train_steps: 300
|
||||
gradient_accumulation_steps: 1
|
||||
|
||||
checkpoint:
|
||||
output_dir: outputs/cosmos25_overfit
|
||||
training_state_checkpointing_steps: 50
|
||||
checkpoints_total_limit: 2
|
||||
|
||||
tracker:
|
||||
project_name: fastvideo_cosmos25
|
||||
run_name: cosmos25_overfit
|
||||
|
||||
model:
|
||||
precondition_outputs: false
|
||||
enable_gradient_checkpointing_type: full
|
||||
|
||||
callbacks:
|
||||
grad_clip:
|
||||
_target_: fastvideo.train.callbacks.grad_clip.GradNormClipCallback
|
||||
max_grad_norm: 1.0
|
||||
validation:
|
||||
_target_: fastvideo.train.callbacks.validation.ValidationCallback
|
||||
pipeline_target: fastvideo.pipelines.basic.cosmos.cosmos2_5_pipeline.Cosmos2_5Pipeline
|
||||
dataset_file: data/cosmos25_overfit_preprocessed/validation_prompts.json
|
||||
every_steps: 150
|
||||
sampling_steps: [35]
|
||||
guidance_scale: 7.0
|
||||
|
||||
pipeline:
|
||||
flow_shift: 1.0
|
||||
@@ -1,7 +1,7 @@
|
||||
cmake_minimum_required(VERSION 3.26 FATAL_ERROR)
|
||||
project(fastvideo-kernel LANGUAGES CXX)
|
||||
|
||||
# Prefer environment variable (used by CI or uv pip install git+repo_addr) if CMake var is not explicitly set.
|
||||
# Prefer environment variable (used by CI or pip install git+repo_addr) if CMake var is not explicitly set.
|
||||
if(NOT DEFINED GPU_BACKEND AND DEFINED ENV{GPU_BACKEND})
|
||||
set(GPU_BACKEND "$ENV{GPU_BACKEND}")
|
||||
endif()
|
||||
|
||||
@@ -61,16 +61,7 @@ has_cmake_arg() {
|
||||
}
|
||||
|
||||
detect_with_torch() {
|
||||
# Prefer the active venv's python directly over `uv run --active --no-project`,
|
||||
# which on some uv versions provisions its own interpreter and misses packages
|
||||
# installed into VIRTUAL_ENV.
|
||||
local py
|
||||
if [[ -n "${VIRTUAL_ENV:-}" && -x "${VIRTUAL_ENV}/bin/python" ]]; then
|
||||
py="${VIRTUAL_ENV}/bin/python"
|
||||
else
|
||||
py="$(command -v python3 || command -v python)"
|
||||
fi
|
||||
"${py}" -c "import torch
|
||||
uv run --active --no-project python -c "import torch
|
||||
if not torch.cuda.is_available():
|
||||
raise RuntimeError('torch.cuda.is_available() is false')
|
||||
mj, mn = torch.cuda.get_device_capability(0)
|
||||
|
||||
@@ -5,11 +5,6 @@ from fastvideo_kernel.ops import (
|
||||
video_sparse_attn,
|
||||
)
|
||||
|
||||
from fastvideo_kernel.block_sparse_attn import (
|
||||
block_sparse_attn,
|
||||
block_sparse_attn_from_indices,
|
||||
)
|
||||
|
||||
from fastvideo_kernel.vmoba import (
|
||||
moba_attn_varlen,
|
||||
process_moba_input,
|
||||
@@ -27,8 +22,6 @@ from fastvideo_kernel.turbodiffusion_ops import (
|
||||
__all__ = [
|
||||
"sliding_tile_attention",
|
||||
"video_sparse_attn",
|
||||
"block_sparse_attn",
|
||||
"block_sparse_attn_from_indices",
|
||||
"moba_attn_varlen",
|
||||
"process_moba_input",
|
||||
"process_moba_output",
|
||||
|
||||
@@ -1,5 +1,3 @@
|
||||
"""Autograd-enabled block-sparse attention. Index-native ops with a bool-mask compat shim."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
@@ -8,11 +6,6 @@ from typing import Tuple
|
||||
import torch
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Backend selection helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _get_sm90_ops():
|
||||
try:
|
||||
from fastvideo_kernel._C import fastvideo_kernel_ops # type: ignore
|
||||
@@ -32,66 +25,38 @@ def _is_sm90() -> bool:
|
||||
|
||||
|
||||
def _force_triton() -> bool:
|
||||
# Force Triton even on SM90 and even if the compiled extension is available.
|
||||
# Useful for CI / debugging / parity testing.
|
||||
return os.environ.get("FASTVIDEO_KERNEL_VSA_FORCE_TRITON", "0") == "1"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Index helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _map_to_index(block_map: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""Compact a bool block_map to (q2k_idx, q2k_num). Legacy path only."""
|
||||
"""
|
||||
Preferred map->index conversion used by the wrapper.
|
||||
|
||||
This wrapper **requires** the Triton implementation.
|
||||
If Triton (or the Triton map_to_index module) is not available, it raises.
|
||||
"""
|
||||
if block_map.dim() == 3:
|
||||
block_map = block_map.unsqueeze(0)
|
||||
if block_map.dim() != 4:
|
||||
raise ValueError(
|
||||
f"block_map must be [B,H,Q,KV] (or [H,Q,KV]), "
|
||||
f"got shape={tuple(block_map.shape)}"
|
||||
)
|
||||
raise ValueError(f"block_map must be [B,H,Q,KV] (or [H,Q,KV]), got shape={tuple(block_map.shape)}")
|
||||
if block_map.dtype != torch.bool:
|
||||
block_map = block_map.to(torch.bool)
|
||||
|
||||
if not block_map.is_cuda:
|
||||
raise RuntimeError(
|
||||
"block_map must be a CUDA tensor (Triton map_to_index required)."
|
||||
)
|
||||
raise RuntimeError("block_map must be a CUDA tensor (Triton map_to_index required).")
|
||||
|
||||
try:
|
||||
from fastvideo_kernel.triton_kernels.index import map_to_index as triton_map_to_index
|
||||
except Exception as e: # pragma: no cover - environment issue
|
||||
from fastvideo_kernel.triton_kernels.index import map_to_index as triton_map_to_index # local import
|
||||
except Exception as e:
|
||||
raise ImportError(
|
||||
"Triton map_to_index is required but not available. "
|
||||
"Ensure Triton is installed and "
|
||||
"fastvideo_kernel.triton_kernels.index is importable."
|
||||
"Ensure Triton is installed and fastvideo_kernel.triton_kernels.index is importable."
|
||||
) from e
|
||||
return triton_map_to_index(block_map)
|
||||
|
||||
|
||||
def _invert_indices_for_backward(
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
num_kv_blocks: int,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
from fastvideo_kernel.triton_kernels.index import invert_indices
|
||||
return invert_indices(q2k_idx, q2k_num, num_kv_blocks=num_kv_blocks)
|
||||
|
||||
|
||||
def _as_int32_contig(t: torch.Tensor, name: str) -> torch.Tensor:
|
||||
"""Return `t` as a contiguous int32 tensor, raising a clear error on CPU input."""
|
||||
if not t.is_cuda:
|
||||
raise RuntimeError(f"{name} must be a CUDA tensor, got device={t.device}")
|
||||
if t.dtype != torch.int32:
|
||||
t = t.to(torch.int32)
|
||||
if not t.is_contiguous():
|
||||
t = t.contiguous()
|
||||
return t
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Triton backend custom ops (index-native)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@torch.library.custom_op(
|
||||
"fastvideo_kernel::block_sparse_attn_triton",
|
||||
mutates_args=(),
|
||||
@@ -101,40 +66,34 @@ def block_sparse_attn_triton(
|
||||
q: torch.Tensor,
|
||||
k: torch.Tensor,
|
||||
v: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import (
|
||||
q = q.contiguous()
|
||||
k = k.contiguous()
|
||||
v = v.contiguous()
|
||||
block_map = block_map.to(torch.bool)
|
||||
q2k_idx, q2k_num = _map_to_index(block_map)
|
||||
|
||||
from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import ( # local import
|
||||
triton_block_sparse_attn_forward,
|
||||
)
|
||||
|
||||
o, M = triton_block_sparse_attn_forward(
|
||||
q.contiguous(),
|
||||
k.contiguous(),
|
||||
v.contiguous(),
|
||||
q2k_idx,
|
||||
q2k_num,
|
||||
variable_block_sizes,
|
||||
)
|
||||
o, M = triton_block_sparse_attn_forward(q, k, v, q2k_idx, q2k_num, variable_block_sizes)
|
||||
return o, M
|
||||
|
||||
|
||||
|
||||
@torch.library.register_fake("fastvideo_kernel::block_sparse_attn_triton")
|
||||
def _block_sparse_attn_triton_fake(
|
||||
q: torch.Tensor,
|
||||
k: torch.Tensor,
|
||||
v: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
o = torch.empty_like(q)
|
||||
M = torch.empty(
|
||||
(q.shape[0], q.shape[1], q.shape[2]),
|
||||
device=q.device,
|
||||
dtype=torch.float32,
|
||||
)
|
||||
M = torch.empty((q.shape[0], q.shape[1], q.shape[2]), device=q.device, dtype=torch.float32)
|
||||
return o, M
|
||||
|
||||
|
||||
@@ -150,32 +109,20 @@ def block_sparse_attn_backward_triton(
|
||||
v: torch.Tensor,
|
||||
o: torch.Tensor,
|
||||
M: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
||||
from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import (
|
||||
grad_output = grad_output.contiguous()
|
||||
block_map = block_map.to(torch.bool)
|
||||
q2k_idx, q2k_num = _map_to_index(block_map)
|
||||
k2q_idx, k2q_num = _map_to_index(block_map.transpose(-1, -2).contiguous())
|
||||
|
||||
from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import ( # local import
|
||||
triton_block_sparse_attn_backward,
|
||||
)
|
||||
|
||||
num_kv_blocks = int(variable_block_sizes.numel())
|
||||
k2q_idx, k2q_num = _invert_indices_for_backward(
|
||||
q2k_idx, q2k_num, num_kv_blocks
|
||||
)
|
||||
# q/k/v are saved from the user-facing inputs and may be non-contiguous;
|
||||
# o/M are kernel outputs so are already contiguous.
|
||||
dq, dk, dv = triton_block_sparse_attn_backward(
|
||||
grad_output.contiguous(),
|
||||
q.contiguous(),
|
||||
k.contiguous(),
|
||||
v.contiguous(),
|
||||
o,
|
||||
M,
|
||||
q2k_idx,
|
||||
q2k_num,
|
||||
k2q_idx,
|
||||
k2q_num,
|
||||
variable_block_sizes,
|
||||
grad_output, q, k, v, o, M, q2k_idx, q2k_num, k2q_idx, k2q_num, variable_block_sizes
|
||||
)
|
||||
return dq, dk, dv
|
||||
|
||||
@@ -188,8 +135,7 @@ def _block_sparse_attn_backward_triton_fake(
|
||||
v: torch.Tensor,
|
||||
o: torch.Tensor,
|
||||
M: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
||||
dq = torch.empty_like(q)
|
||||
@@ -198,28 +144,19 @@ def _block_sparse_attn_backward_triton_fake(
|
||||
return dq, dk, dv
|
||||
|
||||
|
||||
def _setup_context_triton(ctx, inputs, output):
|
||||
q, k, v, q2k_idx, q2k_num, variable_block_sizes = inputs
|
||||
o, M = output
|
||||
ctx.save_for_backward(q, k, v, o, M, q2k_idx, q2k_num, variable_block_sizes)
|
||||
|
||||
|
||||
def _backward_triton(ctx, grad_o, grad_M):
|
||||
q, k, v, o, M, q2k_idx, q2k_num, variable_block_sizes = ctx.saved_tensors
|
||||
dq, dk, dv = block_sparse_attn_backward_triton(
|
||||
grad_o, q, k, v, o, M, q2k_idx, q2k_num, variable_block_sizes
|
||||
)
|
||||
return dq, dk, dv, None, None, None
|
||||
q, k, v, o, M, block_map, variable_block_sizes = ctx.saved_tensors
|
||||
dq, dk, dv = block_sparse_attn_backward_triton(grad_o, q, k, v, o, M, block_map, variable_block_sizes)
|
||||
return dq, dk, dv, None, None
|
||||
|
||||
|
||||
block_sparse_attn_triton.register_autograd(
|
||||
_backward_triton, setup_context=_setup_context_triton
|
||||
)
|
||||
def _setup_context_triton(ctx, inputs, output):
|
||||
q, k, v, block_map, variable_block_sizes = inputs
|
||||
o, M = output
|
||||
ctx.save_for_backward(q, k, v, o, M, block_map, variable_block_sizes)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# SM90 backend custom ops (index-native)
|
||||
# ---------------------------------------------------------------------------
|
||||
block_sparse_attn_triton.register_autograd(_backward_triton, setup_context=_setup_context_triton)
|
||||
|
||||
|
||||
@torch.library.custom_op(
|
||||
@@ -231,21 +168,21 @@ def block_sparse_attn_sm90(
|
||||
q_padded: torch.Tensor,
|
||||
k_padded: torch.Tensor,
|
||||
v_padded: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
block_sparse_fwd, _ = _get_sm90_ops()
|
||||
if block_sparse_fwd is None:
|
||||
raise ImportError("fastvideo_kernel_ops.block_sparse_fwd is not available")
|
||||
|
||||
q_padded = q_padded.contiguous()
|
||||
k_padded = k_padded.contiguous()
|
||||
v_padded = v_padded.contiguous()
|
||||
block_map = block_map.to(torch.bool)
|
||||
q2k_idx, q2k_num = _map_to_index(block_map)
|
||||
|
||||
o_padded, lse_padded = block_sparse_fwd(
|
||||
q_padded.contiguous(),
|
||||
k_padded.contiguous(),
|
||||
v_padded.contiguous(),
|
||||
q2k_idx,
|
||||
q2k_num,
|
||||
variable_block_sizes,
|
||||
q_padded, k_padded, v_padded, q2k_idx, q2k_num, variable_block_sizes.int()
|
||||
)
|
||||
return o_padded, lse_padded
|
||||
|
||||
@@ -255,16 +192,11 @@ def _block_sparse_attn_sm90_fake(
|
||||
q_padded: torch.Tensor,
|
||||
k_padded: torch.Tensor,
|
||||
v_padded: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
o = torch.empty_like(q_padded)
|
||||
lse = torch.empty(
|
||||
(q_padded.shape[0], q_padded.shape[1], q_padded.shape[2], 1),
|
||||
device=q_padded.device,
|
||||
dtype=torch.float32,
|
||||
)
|
||||
lse = torch.empty((q_padded.shape[0], q_padded.shape[1], q_padded.shape[2], 1), device=q_padded.device, dtype=torch.float32)
|
||||
return o, lse
|
||||
|
||||
|
||||
@@ -280,34 +212,30 @@ def block_sparse_attn_backward_sm90(
|
||||
v_padded: torch.Tensor,
|
||||
o_padded: torch.Tensor,
|
||||
lse_padded: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
||||
_, block_sparse_bwd = _get_sm90_ops()
|
||||
if block_sparse_bwd is None:
|
||||
raise ImportError("fastvideo_kernel_ops.block_sparse_bwd is not available")
|
||||
|
||||
num_kv_blocks = int(variable_block_sizes.numel())
|
||||
k2q_idx, k2q_num = _invert_indices_for_backward(
|
||||
q2k_idx, q2k_num, num_kv_blocks
|
||||
)
|
||||
grad_output_padded = grad_output_padded.contiguous()
|
||||
block_map = block_map.to(torch.bool)
|
||||
k2q_idx, k2q_num = _map_to_index(block_map.transpose(-1, -2).contiguous())
|
||||
|
||||
# q/k/v are saved from user-facing inputs; o/lse are kernel outputs.
|
||||
dq, dk, dv = block_sparse_bwd(
|
||||
q_padded.contiguous(),
|
||||
k_padded.contiguous(),
|
||||
v_padded.contiguous(),
|
||||
q_padded,
|
||||
k_padded,
|
||||
v_padded,
|
||||
o_padded,
|
||||
lse_padded,
|
||||
grad_output_padded.contiguous(),
|
||||
grad_output_padded,
|
||||
k2q_idx,
|
||||
k2q_num,
|
||||
variable_block_sizes,
|
||||
variable_block_sizes.int(),
|
||||
)
|
||||
# C++ kernel returns fp32 grads; cast back to the input dtype.
|
||||
out_dtype = grad_output_padded.dtype
|
||||
return dq.to(out_dtype), dk.to(out_dtype), dv.to(out_dtype)
|
||||
# C++ kernel returns fp32 grads; cast back to match PyTorch convention if needed
|
||||
return dq.to(grad_output_padded.dtype), dk.to(grad_output_padded.dtype), dv.to(grad_output_padded.dtype)
|
||||
|
||||
|
||||
@torch.library.register_fake("fastvideo_kernel::block_sparse_attn_backward_sm90")
|
||||
@@ -318,8 +246,7 @@ def _block_sparse_attn_backward_sm90_fake(
|
||||
v_padded: torch.Tensor,
|
||||
o_padded: torch.Tensor,
|
||||
lse_padded: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
||||
dq = torch.empty_like(q_padded)
|
||||
@@ -328,57 +255,21 @@ def _block_sparse_attn_backward_sm90_fake(
|
||||
return dq, dk, dv
|
||||
|
||||
|
||||
def _setup_context_sm90(ctx, inputs, output):
|
||||
q, k, v, q2k_idx, q2k_num, variable_block_sizes = inputs
|
||||
o, lse = output
|
||||
ctx.save_for_backward(q, k, v, o, lse, q2k_idx, q2k_num, variable_block_sizes)
|
||||
|
||||
|
||||
def _backward_sm90(ctx, grad_o, grad_lse):
|
||||
q, k, v, o, lse, q2k_idx, q2k_num, variable_block_sizes = ctx.saved_tensors
|
||||
q, k, v, o, lse, block_map, variable_block_sizes = ctx.saved_tensors
|
||||
dq, dk, dv = block_sparse_attn_backward_sm90(
|
||||
grad_o, q, k, v, o, lse, q2k_idx, q2k_num, variable_block_sizes
|
||||
grad_o, q, k, v, o, lse, block_map, variable_block_sizes
|
||||
)
|
||||
return dq, dk, dv, None, None, None
|
||||
return dq, dk, dv, None, None
|
||||
|
||||
|
||||
block_sparse_attn_sm90.register_autograd(
|
||||
_backward_sm90, setup_context=_setup_context_sm90
|
||||
)
|
||||
def _setup_context_sm90(ctx, inputs, output):
|
||||
q, k, v, block_map, variable_block_sizes = inputs
|
||||
o, lse = output
|
||||
ctx.save_for_backward(q, k, v, o, lse, block_map, variable_block_sizes)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Public API
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def block_sparse_attn_from_indices(
|
||||
q: torch.Tensor,
|
||||
k: torch.Tensor,
|
||||
v: torch.Tensor,
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""Block-sparse attention with autograd, taking compact per-row KV indices."""
|
||||
# Normalize index tensors once at the public boundary so the custom ops
|
||||
# and their fakes can assume int32/contiguous. No-op on well-formed input.
|
||||
q2k_idx = _as_int32_contig(q2k_idx, "q2k_idx")
|
||||
q2k_num = _as_int32_contig(q2k_num, "q2k_num")
|
||||
variable_block_sizes = _as_int32_contig(variable_block_sizes, "variable_block_sizes")
|
||||
|
||||
block_sparse_fwd, block_sparse_bwd = _get_sm90_ops()
|
||||
use_sm90 = (
|
||||
(not _force_triton())
|
||||
and _is_sm90()
|
||||
and block_sparse_fwd is not None
|
||||
and block_sparse_bwd is not None
|
||||
)
|
||||
if use_sm90:
|
||||
return block_sparse_attn_sm90(q, k, v, q2k_idx, q2k_num, variable_block_sizes)
|
||||
# Triton path: supports q_seq_len != kv_seq_len as long as both are padded
|
||||
# to a multiple of the block size (64 tokens).
|
||||
return block_sparse_attn_triton(q, k, v, q2k_idx, q2k_num, variable_block_sizes)
|
||||
block_sparse_attn_sm90.register_autograd(_backward_sm90, setup_context=_setup_context_sm90)
|
||||
|
||||
|
||||
def block_sparse_attn(
|
||||
@@ -388,8 +279,16 @@ def block_sparse_attn(
|
||||
block_map: torch.Tensor,
|
||||
variable_block_sizes: torch.Tensor,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""Bool-mask compat wrapper; prefer block_sparse_attn_from_indices."""
|
||||
q2k_idx, q2k_num = _map_to_index(block_map)
|
||||
return block_sparse_attn_from_indices(
|
||||
q, k, v, q2k_idx, q2k_num, variable_block_sizes
|
||||
)
|
||||
"""
|
||||
Unified block-sparse attention op with autograd support.
|
||||
- On SM90 with compiled extension present: uses fastvideo_kernel_ops.block_sparse_fwd/bwd.
|
||||
- Otherwise: uses Triton implementation (requires q/k/v to have same padded length today).
|
||||
"""
|
||||
block_sparse_fwd, block_sparse_bwd = _get_sm90_ops()
|
||||
if (not _force_triton()) and _is_sm90() and (block_sparse_fwd is not None) and (block_sparse_bwd is not None):
|
||||
return block_sparse_attn_sm90(q, k, v, block_map, variable_block_sizes)
|
||||
# Triton path: supports q_seq_len != kv_seq_len as long as both are padded
|
||||
# to a multiple of the block size (64 tokens).
|
||||
return block_sparse_attn_triton(q, k, v, block_map, variable_block_sizes)
|
||||
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import math
|
||||
import torch
|
||||
from .block_sparse_attn import block_sparse_attn, block_sparse_attn_from_indices
|
||||
from .block_sparse_attn import block_sparse_attn
|
||||
from .triton_kernels.st_attn_triton import sliding_tile_attention_triton
|
||||
|
||||
# Try to load the C++ extension
|
||||
@@ -125,18 +125,13 @@ def video_sparse_attn(
|
||||
out_c = out_c.repeat(1, 1, 1, block_elements,
|
||||
1).view(batch, heads, q_seq_len, dim)
|
||||
|
||||
# Sparse branch: feed top-k indices directly, skipping the bool-mask round-trip.
|
||||
# Sparse branch
|
||||
topk_idx = torch.topk(scores, topk, dim=-1).indices
|
||||
q2k_idx = topk_idx.to(torch.int32).contiguous()
|
||||
q2k_num = torch.full(
|
||||
(batch, heads, q_num_blocks),
|
||||
topk,
|
||||
dtype=torch.int32,
|
||||
device=q.device,
|
||||
)
|
||||
out_s = block_sparse_attn_from_indices(
|
||||
q, k, v, q2k_idx, q2k_num, variable_block_sizes
|
||||
)[0]
|
||||
mask = torch.zeros_like(scores,
|
||||
dtype=torch.bool).scatter_(-1, topk_idx, True)
|
||||
|
||||
# out_s = block_sparse_attn(q, k, v, mask, variable_block_sizes)[0]
|
||||
out_s = block_sparse_attn(q, k, v, mask, variable_block_sizes)[0]
|
||||
|
||||
if compress_attn_weight is not None:
|
||||
return out_c * compress_attn_weight + out_s
|
||||
|
||||
@@ -1,10 +1,9 @@
|
||||
## pytorch sdpa version of block sparse ##
|
||||
from typing import Tuple
|
||||
|
||||
import triton
|
||||
import triton.language as tl
|
||||
import torch
|
||||
|
||||
|
||||
@triton.jit
|
||||
def topk_index_to_map_kernel(
|
||||
map_ptr,
|
||||
@@ -154,114 +153,3 @@ def map_to_index(block_map: torch.Tensor):
|
||||
)
|
||||
|
||||
return index, index_num
|
||||
|
||||
|
||||
@triton.jit
|
||||
def _invert_indices_kernel(
|
||||
q2k_idx_ptr,
|
||||
q2k_num_ptr,
|
||||
k2q_idx_ptr,
|
||||
k2q_num_ptr,
|
||||
q2k_idx_b, q2k_idx_h, q2k_idx_q, q2k_idx_k,
|
||||
q2k_num_b, q2k_num_h, q2k_num_q,
|
||||
k2q_idx_b, k2q_idx_h, k2q_idx_k, k2q_idx_q,
|
||||
k2q_num_b, k2q_num_h, k2q_num_k,
|
||||
MAX_KV_PER_Q: tl.constexpr,
|
||||
):
|
||||
# One program per (b, h, q): reserve a slot in k2q via atomicAdd, write q.
|
||||
pid_b = tl.program_id(0)
|
||||
pid_h = tl.program_id(1)
|
||||
pid_q = tl.program_id(2)
|
||||
|
||||
n = tl.load(
|
||||
q2k_num_ptr
|
||||
+ pid_b * q2k_num_b
|
||||
+ pid_h * q2k_num_h
|
||||
+ pid_q * q2k_num_q
|
||||
)
|
||||
|
||||
q2k_row = (
|
||||
q2k_idx_ptr
|
||||
+ pid_b * q2k_idx_b
|
||||
+ pid_h * q2k_idx_h
|
||||
+ pid_q * q2k_idx_q
|
||||
)
|
||||
|
||||
for i in tl.range(0, MAX_KV_PER_Q):
|
||||
if i < n:
|
||||
kv = tl.load(q2k_row + i * q2k_idx_k)
|
||||
count_ptr = (
|
||||
k2q_num_ptr
|
||||
+ pid_b * k2q_num_b
|
||||
+ pid_h * k2q_num_h
|
||||
+ kv * k2q_num_k
|
||||
)
|
||||
pos = tl.atomic_add(count_ptr, 1)
|
||||
tl.store(
|
||||
k2q_idx_ptr
|
||||
+ pid_b * k2q_idx_b
|
||||
+ pid_h * k2q_idx_h
|
||||
+ kv * k2q_idx_k
|
||||
+ pos * k2q_idx_q,
|
||||
pid_q,
|
||||
)
|
||||
|
||||
|
||||
def invert_indices(
|
||||
q2k_idx: torch.Tensor,
|
||||
q2k_num: torch.Tensor,
|
||||
num_kv_blocks: int,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""Transpose a Q->KV index list into a K->Q one via atomic compaction (GPU)."""
|
||||
if q2k_idx.dim() != 4:
|
||||
raise ValueError(
|
||||
f"q2k_idx must be [B, H, Nq, Mk], got shape={tuple(q2k_idx.shape)}"
|
||||
)
|
||||
if q2k_num.dim() != 3:
|
||||
raise ValueError(
|
||||
f"q2k_num must be [B, H, Nq], got shape={tuple(q2k_num.shape)}"
|
||||
)
|
||||
if not q2k_idx.is_cuda or not q2k_num.is_cuda:
|
||||
raise RuntimeError("invert_indices requires CUDA tensors.")
|
||||
|
||||
B, H, Nq, Mk = q2k_idx.shape
|
||||
if q2k_num.shape != (B, H, Nq):
|
||||
raise ValueError(
|
||||
f"q2k_num shape {tuple(q2k_num.shape)} does not match q2k_idx "
|
||||
f"[B, H, Nq] = {(B, H, Nq)}"
|
||||
)
|
||||
|
||||
q2k_idx = q2k_idx.contiguous()
|
||||
q2k_num = q2k_num.contiguous()
|
||||
if q2k_idx.dtype != torch.int32:
|
||||
q2k_idx = q2k_idx.to(torch.int32)
|
||||
if q2k_num.dtype != torch.int32:
|
||||
q2k_num = q2k_num.to(torch.int32)
|
||||
|
||||
# Any KV block is attended by at most Nq Q blocks (one per Q row), so
|
||||
# `Nq` is a tight upper bound on the compacted K->Q slots.
|
||||
k2q_idx = torch.empty(
|
||||
(B, H, num_kv_blocks, Nq),
|
||||
dtype=torch.int32,
|
||||
device=q2k_idx.device,
|
||||
)
|
||||
k2q_num = torch.zeros(
|
||||
(B, H, num_kv_blocks),
|
||||
dtype=torch.int32,
|
||||
device=q2k_idx.device,
|
||||
)
|
||||
|
||||
grid = (B, H, Nq)
|
||||
_invert_indices_kernel[grid](
|
||||
q2k_idx,
|
||||
q2k_num,
|
||||
k2q_idx,
|
||||
k2q_num,
|
||||
q2k_idx.stride(0), q2k_idx.stride(1), q2k_idx.stride(2), q2k_idx.stride(3),
|
||||
q2k_num.stride(0), q2k_num.stride(1), q2k_num.stride(2),
|
||||
k2q_idx.stride(0), k2q_idx.stride(1), k2q_idx.stride(2), k2q_idx.stride(3),
|
||||
k2q_num.stride(0), k2q_num.stride(1), k2q_num.stride(2),
|
||||
MAX_KV_PER_Q=Mk,
|
||||
)
|
||||
|
||||
return k2q_idx, k2q_num
|
||||
|
||||
@@ -11,7 +11,7 @@ except ImportError:
|
||||
|
||||
def _unsupported(*args, **kwargs):
|
||||
raise ImportError(
|
||||
"flash-attn is not installed. Please install it, e.g., `uv pip install flash-attn`."
|
||||
"flash-attn is not installed. Please install it, e.g., `pip install flash-attn`."
|
||||
)
|
||||
|
||||
_flash_attn_varlen_forward = _unsupported
|
||||
|
||||
@@ -1,67 +0,0 @@
|
||||
# `fastvideo/` — Core Package
|
||||
|
||||
**Generated:** 2026-05-02
|
||||
|
||||
Inference + training framework for video DiTs. Public API entry: `from fastvideo import VideoGenerator, PipelineConfig, SamplingParam`.
|
||||
|
||||
## Public Surface (`__init__.py`)
|
||||
|
||||
```python
|
||||
VideoGenerator # entrypoints/video_generator.py — high-level inference handle
|
||||
PipelineConfig # configs/pipelines/base.py — pipeline wiring dataclass
|
||||
SamplingParam # api/sampling_param.py — runtime sampling knobs
|
||||
```
|
||||
|
||||
CLI entry: `fastvideo` script → `entrypoints/cli/main.py` (subcommands: `generate`, `serve`, `bench`).
|
||||
|
||||
## Layout
|
||||
|
||||
```
|
||||
fastvideo/
|
||||
├── api/ # Schema + presets for the OpenAI-compatible serving layer
|
||||
├── attention/ # Backends + selector (FlashAttn / SageAttn / SDPA / VSA / VMoBA / SLA)
|
||||
├── configs/ # Per-model arch configs + per-pipeline configs (registry-driven)
|
||||
├── dataset/ # Dataloaders (pre-commit excluded — minimal lint surface)
|
||||
├── distributed/ # SP/TP groups, device communicators, init helpers
|
||||
├── entrypoints/ # cli/, openai/, streaming/, video_generator.py
|
||||
├── hooks/ # Runtime hook system for pipelines
|
||||
├── layers/ # Tensor-parallel linears + attention wrappers (port targets)
|
||||
├── models/ # DiT / VAE / encoder / scheduler / loader (pre-commit excluded)
|
||||
├── pipelines/ # basic/<model>/, preprocess/, stages/, training/
|
||||
├── platforms/ # CUDA/ROCm capability + AttentionBackendEnum
|
||||
├── third_party/ # Vendored externals (lint excluded; do not reformat)
|
||||
├── train/ # NEW modular trainer — methods × models × callbacks
|
||||
├── training/ # LEGACY monolithic *_training/distillation_pipeline.py
|
||||
├── worker/ # Multi-process / Ray executors
|
||||
├── workflow/ # Preprocessing workflow base class
|
||||
├── registry.py # Pipeline-config + model-class lookup (canonical)
|
||||
├── envs.py # Env-var declarations
|
||||
├── fastvideo_args.py# Runtime arg dataclass passed through pipelines
|
||||
└── utils.py # FlexibleArgumentParser, qualname resolver, etc.
|
||||
```
|
||||
|
||||
## Where to Look
|
||||
|
||||
| Task | Location |
|
||||
|------|----------|
|
||||
| Add a new pipeline class | `pipelines/basic/<model>/` + `configs/pipelines/<model>.py` + register in `registry.py` |
|
||||
| Add a new model component | `models/<role>/<model>.py` + `configs/models/<role>/<model>.py` |
|
||||
| Wire an existing model into a new pipeline | `pipelines/basic/<model>/presets.py` + reuse stages from `pipelines/stages/` |
|
||||
| Add a converter | `scripts/checkpoint_conversion/<model>_to_*.py` (separate dir, separate AGENTS.md) |
|
||||
| Add an attention backend | `attention/backends/<name>.py` + register in selector |
|
||||
| Add a runtime CLI flag | `fastvideo_args.py` (avoid `argparse` ad-hoc inside stages) |
|
||||
|
||||
## Conventions Specific Here
|
||||
|
||||
- `PipelineStage` subclasses (`pipelines/stages/`) own one verb each (encode, schedule, denoise, decode). Compose, don't fork.
|
||||
- Every pipeline reads from a `PipelineConfig` subclass and a `SamplingParam`. Never read raw env vars inside a stage — go through `fastvideo.envs`.
|
||||
- Logger setup: `from fastvideo.logger import init_logger; logger = init_logger(__name__)`. Do not call `logging.getLogger` directly.
|
||||
- Imports between `train/` and `training/` are **forbidden** — they are independent stacks.
|
||||
|
||||
## Pre-Commit Exclusions (do not assume linted)
|
||||
|
||||
These dirs are listed in `.pre-commit-config.yaml` `exclude`:
|
||||
|
||||
- `fastvideo/third_party/`, `fastvideo/dataset/`, `fastvideo/models/`
|
||||
|
||||
Editing files there will NOT trigger yapf/ruff/mypy/codespell. Format manually if a sibling file shows clear style; do not introduce new violations.
|
||||
@@ -1,5 +1,5 @@
|
||||
from fastvideo.configs.pipelines import PipelineConfig
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
from fastvideo.entrypoints.video_generator import VideoGenerator
|
||||
from fastvideo.version import __version__
|
||||
|
||||
|
||||
@@ -7,37 +7,21 @@ from fastvideo.api.schema import (
|
||||
GenerationPlan,
|
||||
GenerationRequest,
|
||||
GeneratorConfig,
|
||||
GpuPoolConfig,
|
||||
InputConfig,
|
||||
OffloadConfig,
|
||||
OutputConfig,
|
||||
ParallelismConfig,
|
||||
PipelineSelection,
|
||||
PlannedStage,
|
||||
PromptEnhancerConfig,
|
||||
PromptSafetyConfig,
|
||||
QuantizationConfig,
|
||||
RequestRuntimeConfig,
|
||||
RunConfig,
|
||||
SamplingConfig,
|
||||
ServeConfig,
|
||||
ServerConfig,
|
||||
StreamingConfig,
|
||||
WarmupConfig,
|
||||
)
|
||||
from fastvideo.api.errors import ConfigValidationError
|
||||
from fastvideo.api.overrides import apply_overrides, parse_cli_overrides
|
||||
from fastvideo.api.presets import (
|
||||
InferencePreset,
|
||||
PresetStageSpec,
|
||||
get_all_preset_names,
|
||||
get_preset,
|
||||
get_presets_for_family,
|
||||
register_preset,
|
||||
validate_preset_selection,
|
||||
validate_stage_names,
|
||||
validate_stage_overrides,
|
||||
)
|
||||
from fastvideo.api.parser import (
|
||||
config_to_dict,
|
||||
load_config,
|
||||
@@ -47,7 +31,6 @@ from fastvideo.api.parser import (
|
||||
parse_config,
|
||||
)
|
||||
from fastvideo.api.results import GenerationResult
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
|
||||
__all__ = [
|
||||
"CompileConfig",
|
||||
@@ -59,26 +42,18 @@ __all__ = [
|
||||
"GenerationPlan",
|
||||
"GenerationRequest",
|
||||
"GeneratorConfig",
|
||||
"GpuPoolConfig",
|
||||
"InputConfig",
|
||||
"OffloadConfig",
|
||||
"OutputConfig",
|
||||
"ParallelismConfig",
|
||||
"PipelineSelection",
|
||||
"PlannedStage",
|
||||
"PromptEnhancerConfig",
|
||||
"PromptSafetyConfig",
|
||||
"QuantizationConfig",
|
||||
"RequestRuntimeConfig",
|
||||
"RunConfig",
|
||||
"SamplingConfig",
|
||||
"SamplingParam",
|
||||
"ServeConfig",
|
||||
"ServerConfig",
|
||||
"StreamingConfig",
|
||||
"WarmupConfig",
|
||||
"InferencePreset",
|
||||
"PresetStageSpec",
|
||||
"apply_overrides",
|
||||
"config_to_dict",
|
||||
"load_config",
|
||||
@@ -86,12 +61,5 @@ __all__ = [
|
||||
"load_run_config",
|
||||
"load_serve_config",
|
||||
"parse_cli_overrides",
|
||||
"get_all_preset_names",
|
||||
"get_preset",
|
||||
"get_presets_for_family",
|
||||
"parse_config",
|
||||
"register_preset",
|
||||
"validate_preset_selection",
|
||||
"validate_stage_names",
|
||||
"validate_stage_overrides",
|
||||
]
|
||||
|
||||
+95
-211
@@ -7,17 +7,14 @@ from dataclasses import fields, is_dataclass
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from fastvideo.api.overrides import apply_overrides, normalize_overrides
|
||||
from fastvideo.api.overrides import apply_overrides, parse_cli_overrides
|
||||
from fastvideo.api.parser import config_to_dict, load_raw_config, parse_config
|
||||
from fastvideo.api.request_metadata import (
|
||||
EXPLICIT_PATHS_ATTR,
|
||||
EXPLICIT_REQUEST_ATTR,
|
||||
bind_generation_request_raw,
|
||||
get_explicit_paths,
|
||||
reset_tracking_roots,
|
||||
refresh_generation_request_raw,
|
||||
)
|
||||
from fastvideo.api.schema import (
|
||||
CompileConfig,
|
||||
ContinuationState,
|
||||
GenerationRequest,
|
||||
GeneratorConfig,
|
||||
InputConfig,
|
||||
@@ -25,12 +22,8 @@ from fastvideo.api.schema import (
|
||||
RequestRuntimeConfig,
|
||||
SamplingConfig,
|
||||
)
|
||||
from fastvideo.api.sampling_param import SamplingParam
|
||||
from fastvideo.configs.sample import SamplingParam
|
||||
from fastvideo.fastvideo_args import FastVideoArgs
|
||||
from fastvideo.pipelines.basic.ltx2.stage_overrides import (
|
||||
refine_preset_override_fields,
|
||||
refine_stage_override_fields,
|
||||
)
|
||||
from fastvideo.utils import shallow_asdict
|
||||
|
||||
_INPUT_FIELD_NAMES = {field.name for field in fields(InputConfig)}
|
||||
@@ -44,10 +37,6 @@ _LEGACY_REQUEST_ALIASES = {
|
||||
_REQUEST_PIPELINE_OVERRIDE_FIELDS = frozenset({
|
||||
"embedded_cfg_scale",
|
||||
})
|
||||
# torch.compile kwargs that map to first-class CompileConfig fields.
|
||||
_COMPILE_TYPED_KEYS = ("backend", "fullgraph", "mode", "dynamic")
|
||||
# LTX-2 refine flat kwargs (init + per-request) known to FastVideoArgs.
|
||||
_LTX2_REFINE_FLAT_KEYS = (refine_preset_override_fields() | refine_stage_override_fields())
|
||||
|
||||
|
||||
def normalize_generator_config(config: GeneratorConfig | Mapping[str, Any], ) -> GeneratorConfig:
|
||||
@@ -61,7 +50,7 @@ def load_generator_config_from_file(
|
||||
overrides: list[str] | Mapping[str, Any] | None = None,
|
||||
) -> GeneratorConfig:
|
||||
raw = load_raw_config(path)
|
||||
normalized_overrides = normalize_overrides(overrides)
|
||||
normalized_overrides = _normalize_overrides(overrides)
|
||||
|
||||
if _looks_like_run_or_serve_config(raw):
|
||||
if normalized_overrides:
|
||||
@@ -90,8 +79,6 @@ def legacy_from_pretrained_to_config(
|
||||
components: dict[str, Any] = {}
|
||||
quantization: dict[str, Any] = {}
|
||||
experimental: dict[str, Any] = {}
|
||||
preset_overrides: dict[str, Any] = {}
|
||||
preset_refine: dict[str, Any] = {}
|
||||
|
||||
for key, value in kwargs.items():
|
||||
if key == "revision":
|
||||
@@ -118,33 +105,8 @@ def legacy_from_pretrained_to_config(
|
||||
offload["pin_cpu_memory"] = value
|
||||
elif key == "enable_torch_compile":
|
||||
compile_config["enabled"] = value
|
||||
elif key == "enable_torch_compile_text_encoder":
|
||||
compile_config["text_encoder_enabled"] = value
|
||||
elif key == "torch_compile_kwargs":
|
||||
remaining: dict[str, Any] = (dict(deepcopy(value)) if isinstance(value, Mapping) else {})
|
||||
for first_class in _COMPILE_TYPED_KEYS:
|
||||
if first_class in remaining:
|
||||
compile_config[first_class] = remaining.pop(first_class)
|
||||
if remaining:
|
||||
compile_config["extras"] = remaining
|
||||
elif key == "ltx2_vae_tiling":
|
||||
pipeline["vae_tiling"] = value
|
||||
elif key == "config_model_path":
|
||||
components["config_root"] = value
|
||||
elif key == "ltx2_refine_enabled":
|
||||
preset_refine["enabled"] = value
|
||||
elif key == "ltx2_refine_upsampler_path":
|
||||
# Empty string means "no upsampler"; keep typed None.
|
||||
components["upsampler_weights"] = value or None
|
||||
elif key == "ltx2_refine_lora_path":
|
||||
# Empty string means "no refine LoRA"; keep typed None.
|
||||
components["lora_path"] = value or None
|
||||
elif key == "ltx2_refine_add_noise":
|
||||
preset_refine["add_noise"] = value
|
||||
elif key == "ltx2_refine_num_inference_steps":
|
||||
preset_refine["num_inference_steps"] = value
|
||||
elif key == "ltx2_refine_guidance_scale":
|
||||
preset_refine["guidance_scale"] = value
|
||||
compile_config["kwargs"] = deepcopy(value)
|
||||
elif key in {"enable_stage_verification", "use_fsdp_inference", "disable_autocast"}:
|
||||
engine[key] = value
|
||||
elif key == "override_text_encoder_quant":
|
||||
@@ -184,10 +146,6 @@ def legacy_from_pretrained_to_config(
|
||||
|
||||
if components:
|
||||
pipeline["components"] = components
|
||||
if preset_refine:
|
||||
preset_overrides["refine"] = preset_refine
|
||||
if preset_overrides:
|
||||
pipeline["preset_overrides"] = preset_overrides
|
||||
if experimental:
|
||||
pipeline["experimental"] = experimental
|
||||
if pipeline:
|
||||
@@ -199,12 +157,16 @@ def legacy_from_pretrained_to_config(
|
||||
def generator_config_to_fastvideo_args(config: GeneratorConfig | Mapping[str, Any], ) -> FastVideoArgs:
|
||||
normalized = normalize_generator_config(config)
|
||||
unsupported = []
|
||||
if normalized.pipeline.preset is not None:
|
||||
unsupported.append("pipeline.preset")
|
||||
if normalized.pipeline.preset_version is not None:
|
||||
unsupported.append("pipeline.preset_version")
|
||||
if normalized.pipeline.profile is not None:
|
||||
unsupported.append("pipeline.profile")
|
||||
if normalized.pipeline.profile_version is not None:
|
||||
unsupported.append("pipeline.profile_version")
|
||||
if normalized.pipeline.components.config_root is not None:
|
||||
unsupported.append("pipeline.components.config_root")
|
||||
if normalized.pipeline.components.vae_weights is not None:
|
||||
unsupported.append("pipeline.components.vae_weights")
|
||||
if normalized.pipeline.components.upsampler_weights is not None:
|
||||
unsupported.append("pipeline.components.upsampler_weights")
|
||||
if unsupported:
|
||||
joined = ", ".join(unsupported)
|
||||
raise NotImplementedError(f"VideoGenerator compatibility adapter does not support {joined} yet")
|
||||
@@ -228,21 +190,13 @@ def generator_config_to_fastvideo_args(config: GeneratorConfig | Mapping[str, An
|
||||
"vae_cpu_offload": engine.offload.vae,
|
||||
"pin_cpu_memory": engine.offload.pin_cpu_memory,
|
||||
"enable_torch_compile": engine.compile.enabled,
|
||||
"torch_compile_kwargs": _compile_config_to_torch_kwargs(engine.compile),
|
||||
"torch_compile_kwargs": deepcopy(engine.compile.kwargs),
|
||||
"enable_stage_verification": engine.enable_stage_verification,
|
||||
"use_fsdp_inference": engine.use_fsdp_inference,
|
||||
"disable_autocast": engine.disable_autocast,
|
||||
}
|
||||
if normalized.pipeline.workload_type is not None:
|
||||
kwargs["workload_type"] = normalized.pipeline.workload_type
|
||||
if normalized.pipeline.vae_tiling is not None:
|
||||
kwargs["ltx2_vae_tiling"] = normalized.pipeline.vae_tiling
|
||||
if engine.compile.text_encoder_enabled is not None:
|
||||
# ``FastVideoArgs.from_kwargs`` filters to declared fields, so
|
||||
# this is a no-op on the current legacy path. Emit anyway so the
|
||||
# realtime runtime (PR 7.6) — which reads from the kwargs dict
|
||||
# before FastVideoArgs filtering — can pick it up once wired.
|
||||
kwargs["enable_torch_compile_text_encoder"] = (engine.compile.text_encoder_enabled)
|
||||
|
||||
quantization = engine.quantization
|
||||
if quantization is not None and quantization.text_encoder_quant is not None:
|
||||
@@ -265,18 +219,8 @@ def generator_config_to_fastvideo_args(config: GeneratorConfig | Mapping[str, An
|
||||
kwargs["init_weights_from_safetensors"] = components.transformer_weights
|
||||
if components.transformer_2_weights is not None:
|
||||
kwargs["init_weights_from_safetensors_2"] = components.transformer_2_weights
|
||||
if components.config_root is not None:
|
||||
kwargs["config_model_path"] = components.config_root
|
||||
if components.upsampler_weights is not None:
|
||||
kwargs["ltx2_refine_upsampler_path"] = components.upsampler_weights
|
||||
|
||||
preset_overrides = deepcopy(normalized.pipeline.preset_overrides)
|
||||
refine = preset_overrides.pop("refine", None)
|
||||
if isinstance(refine, Mapping):
|
||||
for key in _LTX2_REFINE_FLAT_KEYS:
|
||||
if key in refine:
|
||||
kwargs[f"ltx2_refine_{key}"] = refine[key]
|
||||
kwargs.update(preset_overrides)
|
||||
kwargs.update(deepcopy(normalized.pipeline.profile_overrides))
|
||||
kwargs.update(deepcopy(normalized.pipeline.experimental))
|
||||
return FastVideoArgs.from_kwargs(**kwargs)
|
||||
|
||||
@@ -284,9 +228,9 @@ def generator_config_to_fastvideo_args(config: GeneratorConfig | Mapping[str, An
|
||||
def normalize_generation_request(request: GenerationRequest | Mapping[str, Any], ) -> GenerationRequest:
|
||||
normalized = (request if isinstance(request, GenerationRequest) else parse_config(GenerationRequest, request))
|
||||
|
||||
if not hasattr(normalized, EXPLICIT_PATHS_ATTR):
|
||||
# Request wasn't bound through the parser (e.g. constructed
|
||||
# directly). Treat every currently-set field as explicit.
|
||||
if hasattr(normalized, EXPLICIT_REQUEST_ATTR):
|
||||
refresh_generation_request_raw(normalized)
|
||||
else:
|
||||
bind_generation_request_raw(normalized, _serialize_generation_request(normalized))
|
||||
return normalized
|
||||
|
||||
@@ -326,24 +270,16 @@ def request_to_sampling_param(
|
||||
) -> SamplingParam:
|
||||
if request.plan is not None:
|
||||
raise NotImplementedError("GenerationRequest.plan is not wired into VideoGenerator yet")
|
||||
if request.state is not None:
|
||||
raise NotImplementedError("GenerationRequest.state is not wired into VideoGenerator yet")
|
||||
|
||||
sampling_param = SamplingParam.from_pretrained(model_path)
|
||||
if request.state is not None:
|
||||
_validate_continuation_state(request.state)
|
||||
sampling_param.continuation_state = request.state
|
||||
if request.output.return_state:
|
||||
sampling_param.return_continuation_state = True
|
||||
updates = explicit_request_updates(request)
|
||||
updates = _explicit_request_updates(request)
|
||||
|
||||
for key, value in updates.items():
|
||||
if hasattr(sampling_param, key):
|
||||
setattr(sampling_param, key, deepcopy(value))
|
||||
elif key in _REQUEST_PIPELINE_OVERRIDE_FIELDS:
|
||||
continue
|
||||
elif value == _SCHEMA_DEFAULT_UPDATES.get(key, _MISSING):
|
||||
# Schema-default field that isn't on SamplingParam; tolerated
|
||||
# because direct GenerationRequest(...) construction has no
|
||||
# way to distinguish "user set" from "schema default".
|
||||
elif key in _REQUEST_PIPELINE_OVERRIDE_FIELDS or _is_supported_as_default_only(key, value):
|
||||
continue
|
||||
else:
|
||||
raise ValueError(f"Request field {key!r} is not supported by sampling params for {model_path}")
|
||||
@@ -360,12 +296,10 @@ def expand_request_prompt_batch(request: GenerationRequest, ) -> list[Generation
|
||||
requests: list[GenerationRequest] = []
|
||||
for index, prompt in enumerate(request.prompt):
|
||||
single_request = deepcopy(request)
|
||||
# deepcopy preserves the tracking-root cycle, but re-pin roots
|
||||
# defensively so that subsequent setattrs record on the copy.
|
||||
reset_tracking_roots(single_request)
|
||||
single_request.prompt = prompt
|
||||
_fan_out_batched_input_value(request, single_request, "image_path", index)
|
||||
_fan_out_batched_input_value(request, single_request, "video_path", index)
|
||||
_fan_out_explicit_request_metadata(request, single_request, index, prompt)
|
||||
requests.append(single_request)
|
||||
return requests
|
||||
|
||||
@@ -374,23 +308,12 @@ def _looks_like_run_or_serve_config(raw: Mapping[str, Any]) -> bool:
|
||||
return isinstance(raw.get("generator"), Mapping)
|
||||
|
||||
|
||||
def _compile_config_to_torch_kwargs(compile_config: CompileConfig, ) -> dict[str, Any]:
|
||||
"""Flatten typed ``CompileConfig`` back to a ``torch_compile_kwargs``
|
||||
dict that the legacy ``FastVideoArgs`` path still expects.
|
||||
|
||||
Typed first-class fields (:attr:`backend`, :attr:`fullgraph`,
|
||||
:attr:`mode`, :attr:`dynamic`) are only emitted when the user set
|
||||
them explicitly (non-``None``). ``extras`` is merged on top for any
|
||||
uncommon kwargs.
|
||||
"""
|
||||
out: dict[str, Any] = {}
|
||||
for key in _COMPILE_TYPED_KEYS:
|
||||
value = getattr(compile_config, key)
|
||||
if value is not None:
|
||||
out[key] = value
|
||||
if compile_config.extras:
|
||||
out.update(deepcopy(compile_config.extras))
|
||||
return out
|
||||
def _normalize_overrides(overrides: list[str] | Mapping[str, Any] | None, ) -> dict[str, Any] | None:
|
||||
if not overrides:
|
||||
return None
|
||||
if isinstance(overrides, list):
|
||||
return parse_cli_overrides(overrides)
|
||||
return dict(overrides)
|
||||
|
||||
|
||||
def _sampling_param_to_request_raw(sampling_param: SamplingParam | None, ) -> dict[str, Any]:
|
||||
@@ -431,83 +354,20 @@ def _apply_request_field(
|
||||
|
||||
def request_to_pipeline_overrides(request: GenerationRequest) -> dict[str, Any]:
|
||||
overrides: dict[str, Any] = {}
|
||||
for key, value in explicit_request_updates(request).items():
|
||||
for key, value in _explicit_request_updates(request).items():
|
||||
if key in _REQUEST_PIPELINE_OVERRIDE_FIELDS:
|
||||
overrides[key] = deepcopy(value)
|
||||
return overrides
|
||||
|
||||
|
||||
def explicit_request_updates(request: GenerationRequest) -> dict[str, Any]:
|
||||
"""Project a ``GenerationRequest`` down to *explicitly set* fields only.
|
||||
def _explicit_request_updates(request: GenerationRequest) -> dict[str, Any]:
|
||||
raw = getattr(request, EXPLICIT_REQUEST_ATTR, None)
|
||||
if raw is None:
|
||||
raw = _serialize_generation_request(request)
|
||||
|
||||
Returns a flat kwargs dict suitable for merging into a generator call.
|
||||
The projection uses ``_fastvideo_explicit_paths`` (populated during
|
||||
``parse_config`` / raw binding) so schema defaults on the dataclass
|
||||
are **not** emitted — only paths the caller/operator actually wrote.
|
||||
|
||||
This is what makes ``ServeConfig.default_request`` work as an
|
||||
operator-pinned baseline rather than a full override: a YAML with just
|
||||
``sampling.seed: 42`` yields ``{"seed": 42}``, not the full sampling
|
||||
config with its 15 schema defaults.
|
||||
|
||||
Precondition: the request must carry ``_fastvideo_explicit_paths`` —
|
||||
populated by :func:`fastvideo.api.parser.parse_config` or
|
||||
:func:`fastvideo.api.compat.normalize_generation_request`. Calling on
|
||||
a raw ``GenerationRequest()`` asserts.
|
||||
"""
|
||||
assert hasattr(request,
|
||||
EXPLICIT_PATHS_ATTR), ("GenerationRequest reached explicit_request_updates without tracking; "
|
||||
"every entry point must route through normalize_generation_request "
|
||||
"or parse_config first")
|
||||
paths = get_explicit_paths(request)
|
||||
raw = _build_sparse_raw_from_paths(request, paths)
|
||||
return _extract_request_updates(raw)
|
||||
|
||||
|
||||
def _build_sparse_raw_from_paths(
|
||||
request: GenerationRequest,
|
||||
paths: frozenset[str],
|
||||
) -> dict[str, Any]:
|
||||
result: dict[str, Any] = {}
|
||||
for path in paths:
|
||||
parts = path.split(".")
|
||||
value = _read_dotted_path(request, parts)
|
||||
if value is _MISSING:
|
||||
continue
|
||||
_set_dotted_path(result, parts, deepcopy(value))
|
||||
return result
|
||||
|
||||
|
||||
def _read_dotted_path(obj: Any, parts: list[str]) -> Any:
|
||||
for part in parts:
|
||||
if is_dataclass(obj) and not isinstance(obj, type):
|
||||
if not hasattr(obj, part):
|
||||
return _MISSING
|
||||
obj = getattr(obj, part)
|
||||
elif isinstance(obj, Mapping):
|
||||
if part not in obj:
|
||||
return _MISSING
|
||||
obj = obj[part]
|
||||
else:
|
||||
return _MISSING
|
||||
return obj
|
||||
|
||||
|
||||
def _set_dotted_path(
|
||||
target: dict[str, Any],
|
||||
parts: list[str],
|
||||
value: Any,
|
||||
) -> None:
|
||||
cursor = target
|
||||
for part in parts[:-1]:
|
||||
nxt = cursor.get(part)
|
||||
if not isinstance(nxt, dict):
|
||||
nxt = {}
|
||||
cursor[part] = nxt
|
||||
cursor = nxt
|
||||
cursor[parts[-1]] = value
|
||||
|
||||
|
||||
def _extract_request_updates(raw: Mapping[str, Any]) -> dict[str, Any]:
|
||||
updates: dict[str, Any] = {}
|
||||
if "negative_prompt" in raw:
|
||||
@@ -551,40 +411,6 @@ def _serialize_generation_request(request: GenerationRequest) -> dict[str, Any]:
|
||||
return deepcopy(config_to_dict(request))
|
||||
|
||||
|
||||
_SCHEMA_DEFAULT_UPDATES = _extract_request_updates(config_to_dict(GenerationRequest()))
|
||||
|
||||
_KNOWN_CONTINUATION_KINDS: set[str] = set()
|
||||
|
||||
|
||||
def register_continuation_kind(kind: str) -> None:
|
||||
"""Register a :class:`ContinuationState.kind` as recognized.
|
||||
|
||||
PR 7 wires the envelope through; per-kind payload deserializers live
|
||||
with each model family (e.g. ``fastvideo.pipelines.basic.ltx2.
|
||||
continuation.LTX2ContinuationState``). The registry lets the
|
||||
public-API compat layer validate the kind early, before the state
|
||||
reaches the pipeline.
|
||||
"""
|
||||
if not isinstance(kind, str) or not kind:
|
||||
raise ValueError("ContinuationState kind must be a non-empty string")
|
||||
_KNOWN_CONTINUATION_KINDS.add(kind)
|
||||
|
||||
|
||||
def _validate_continuation_state(state: ContinuationState) -> None:
|
||||
if not isinstance(state.kind, str) or not state.kind:
|
||||
raise ValueError("GenerationRequest.state.kind must be a non-empty string; got "
|
||||
f"{state.kind!r}")
|
||||
if not isinstance(state.payload, Mapping):
|
||||
raise ValueError(f"GenerationRequest.state.payload must be a mapping; got "
|
||||
f"{type(state.payload).__name__}")
|
||||
if state.kind not in _KNOWN_CONTINUATION_KINDS:
|
||||
known = sorted(_KNOWN_CONTINUATION_KINDS)
|
||||
raise ValueError(f"Unknown ContinuationState kind {state.kind!r}; registered "
|
||||
f"kinds: {known}. Import the model family that owns this kind "
|
||||
"(e.g. `import fastvideo.pipelines.basic.ltx2.continuation`) "
|
||||
"to register it, or drop the state field.")
|
||||
|
||||
|
||||
def _fan_out_batched_input_value(
|
||||
source_request: GenerationRequest,
|
||||
target_request: GenerationRequest,
|
||||
@@ -598,6 +424,29 @@ def _fan_out_batched_input_value(
|
||||
setattr(target_request.inputs, field_name, deepcopy(value[index]))
|
||||
|
||||
|
||||
def _fan_out_explicit_request_metadata(
|
||||
source_request: GenerationRequest,
|
||||
target_request: GenerationRequest,
|
||||
index: int,
|
||||
prompt: str,
|
||||
) -> None:
|
||||
raw = getattr(source_request, EXPLICIT_REQUEST_ATTR, None)
|
||||
if raw is None:
|
||||
return
|
||||
|
||||
raw = deepcopy(raw)
|
||||
raw["prompt"] = prompt
|
||||
inputs = raw.get("inputs")
|
||||
if isinstance(inputs, dict):
|
||||
for field_name in ("image_path", "video_path"):
|
||||
value = inputs.get(field_name)
|
||||
if isinstance(value, list):
|
||||
_validate_batched_input_length(source_request.prompt, value, field_name)
|
||||
inputs[field_name] = deepcopy(value[index])
|
||||
|
||||
setattr(target_request, EXPLICIT_REQUEST_ATTR, raw)
|
||||
|
||||
|
||||
def _validate_batched_input_length(
|
||||
prompts: str | list[str] | None,
|
||||
values: list[Any],
|
||||
@@ -609,15 +458,50 @@ def _validate_batched_input_length(
|
||||
raise ValueError(f"GenerationRequest.inputs.{field_name} must have the same length as request.prompt")
|
||||
|
||||
|
||||
def _is_supported_as_default_only(key: str, value: Any) -> bool:
|
||||
default_value = _DEFAULT_REQUEST_UPDATES.get(key, _MISSING)
|
||||
return default_value is not _MISSING and _values_equal(value, default_value)
|
||||
|
||||
|
||||
def _collect_non_default_fields(
|
||||
value: Any,
|
||||
default: Any,
|
||||
) -> dict[str, Any]:
|
||||
if not (is_dataclass(value) and is_dataclass(default)):
|
||||
return {}
|
||||
|
||||
result: dict[str, Any] = {}
|
||||
for field in fields(value):
|
||||
current = getattr(value, field.name)
|
||||
default_value = getattr(default, field.name)
|
||||
if is_dataclass(current) and is_dataclass(default_value):
|
||||
nested = _collect_non_default_fields(current, default_value)
|
||||
if nested:
|
||||
result[field.name] = nested
|
||||
continue
|
||||
if not _values_equal(current, default_value):
|
||||
result[field.name] = deepcopy(current)
|
||||
return result
|
||||
|
||||
|
||||
def _values_equal(left: Any, right: Any) -> bool:
|
||||
if left is right:
|
||||
return True
|
||||
try:
|
||||
return bool(left == right)
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
_DEFAULT_REQUEST_UPDATES = _extract_request_updates(config_to_dict(GenerationRequest()))
|
||||
|
||||
__all__ = [
|
||||
"explicit_request_updates",
|
||||
"generator_config_to_fastvideo_args",
|
||||
"legacy_from_pretrained_to_config",
|
||||
"legacy_generate_call_to_request",
|
||||
"load_generator_config_from_file",
|
||||
"normalize_generation_request",
|
||||
"normalize_generator_config",
|
||||
"register_continuation_kind",
|
||||
"request_to_pipeline_overrides",
|
||||
"request_to_sampling_param",
|
||||
]
|
||||
|
||||
@@ -45,15 +45,6 @@ def apply_overrides(config: Mapping[str, Any], overrides: Mapping[str, Any]) ->
|
||||
return merged
|
||||
|
||||
|
||||
def normalize_overrides(overrides: list[str] | Mapping[str, Any] | None, ) -> dict[str, Any] | None:
|
||||
"""Normalize a CLI list or mapping of overrides into a flat dict."""
|
||||
if not overrides:
|
||||
return None
|
||||
if isinstance(overrides, list):
|
||||
return parse_cli_overrides(overrides)
|
||||
return dict(overrides)
|
||||
|
||||
|
||||
def _apply_single_override(config: dict[str, Any], dotted_key: str, value: Any) -> None:
|
||||
parts = dotted_key.split(".")
|
||||
if not all(parts):
|
||||
@@ -107,4 +98,4 @@ def _normalize_override_key(key: str) -> str:
|
||||
return key.replace("-", "_")
|
||||
|
||||
|
||||
__all__ = ["apply_overrides", "normalize_overrides", "parse_cli_overrides"]
|
||||
__all__ = ["apply_overrides", "parse_cli_overrides"]
|
||||
|
||||
+10
-2
@@ -11,7 +11,7 @@ from typing import Any, Literal, TypeVar, Union, get_args, get_origin, get_type_
|
||||
import yaml
|
||||
|
||||
from fastvideo.api.errors import ConfigValidationError
|
||||
from fastvideo.api.overrides import apply_overrides, normalize_overrides
|
||||
from fastvideo.api.overrides import apply_overrides, parse_cli_overrides
|
||||
from fastvideo.api.request_metadata import (
|
||||
bind_generation_request_raw,
|
||||
bind_run_config_raw,
|
||||
@@ -64,7 +64,7 @@ def load_config(
|
||||
) -> T:
|
||||
"""Load a typed config object from YAML or JSON."""
|
||||
raw = load_raw_config(path)
|
||||
normalized_overrides = normalize_overrides(overrides)
|
||||
normalized_overrides = _normalize_overrides(overrides)
|
||||
if normalized_overrides:
|
||||
raw = apply_overrides(raw, normalized_overrides)
|
||||
return parse_config(config_type, raw)
|
||||
@@ -108,6 +108,14 @@ def _load_raw_mapping(handle: Any, config_path: Path) -> Any:
|
||||
raise ValueError(f"Unsupported config file format: {config_path}")
|
||||
|
||||
|
||||
def _normalize_overrides(overrides: list[str] | Mapping[str, Any] | None, ) -> dict[str, Any] | None:
|
||||
if not overrides:
|
||||
return None
|
||||
if isinstance(overrides, list):
|
||||
return parse_cli_overrides(overrides)
|
||||
return dict(overrides)
|
||||
|
||||
|
||||
class _SchemaParser:
|
||||
|
||||
def parse_dataclass(
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user