nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[ci] make GPU validation change-aware (#1747)

Browse Source
This commit is contained in:
William Lin
2026-08-25 21:26:25 -07:00
committed by GitHub
parent 6388db815b
commit 9212f4f218
89 changed files with 3139 additions and 937 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/_template-build-image.yml
+1
View File
@@ -190,6 +190,7 @@ jobs:
if: ${{ !inputs.push_by_digest }}
run: |
echo "✅ Python ${{ inputs.python_version }} image successfully built and pushed to ${{ steps.image.outputs.name }}:${{ inputs.tag_suffix }}-sha-${GITHUB_SHA::7}"
echo "Digest: ${{ steps.build-push.outputs.digest }}"
echo "To run tests with this image, manually trigger the 'Run Tests' workflow."
- name: Digest success message
.github/workflows/ci-aggregate-status.yml
+39 -25
View File
@@ -26,29 +26,48 @@ jobs:
per_page: 100,
});
const bkStatuses = data.statuses.filter(
s => s.context.startsWith('buildkite/ci/')
);
const FASTCHECK_PREFIX = 'buildkite/ci/microscope-';
// Buildkite derives the GitHub context prefix from the label emoji.
// Keep hard Full Suite lanes in test-tube/bar-chart namespaces and
// Fastcheck lanes in microscope so targeted reruns cannot clear the
// wrong aggregate status. Automatic PR jobs use pr-fastcheck while
// slash-command and Full Suite jobs use ci; normalize the suffix
// and keep the newest status for each logical lane.
const FASTCHECK_PREFIXES = [
'buildkite/pr-fastcheck/microscope-',
'buildkite/ci/microscope-',
];
const FULL_SUITE_PREFIXES = [
'buildkite/ci/test-tube-',
'buildkite/ci/bar-chart-',
];
const fastcheck = bkStatuses.filter(
s => s.context.startsWith(FASTCHECK_PREFIX)
);
const fullSuite = bkStatuses.filter(
s => FULL_SUITE_PREFIXES.some(p => s.context.startsWith(p))
);
function newestByLane(prefixes) {
const statuses = new Map();
for (const status of data.statuses) {
const prefix = prefixes.find(p => status.context.startsWith(p));
if (!prefix) continue;
const lane = status.context.slice(prefix.length);
const previous = statuses.get(lane);
if (!previous || Date.parse(status.updated_at) > Date.parse(previous.updated_at)) {
statuses.set(lane, status);
}
}
return statuses;
}
if (
fastcheck.length > 0
&& fastcheck.every(s => s.state === 'success')
) {
const fastcheck = newestByLane(FASTCHECK_PREFIXES);
const fullSuiteOnly = newestByLane(FULL_SUITE_PREFIXES);
const fastcheckPassed =
fastcheck.size === 6
&& [...fastcheck.values()].every(s => s.state === 'success');
const fullSuitePassed =
fastcheckPassed
&& fullSuiteOnly.size === 14
&& [...fullSuiteOnly.values()].every(s => s.state === 'success');
if (fastcheckPassed) {
core.info(
`All ${fastcheck.length} fastcheck tests passed — updating fastcheck-passed`
`All ${fastcheck.size} fastcheck tests passed — updating fastcheck-passed`
);
await github.rest.repos.createCommitStatus({
owner: context.repo.owner,
@@ -56,17 +75,13 @@ jobs:
sha,
state: 'success',
context: 'fastcheck-passed',
description:
`All ${fastcheck.length} fastcheck tests passed`,
description: `All ${fastcheck.size} fastcheck tests passed`,
});
}
if (
fullSuite.length > 0
&& fullSuite.every(s => s.state === 'success')
) {
if (fullSuitePassed) {
core.info(
`All ${fullSuite.length} full suite tests passed — updating full-suite-passed`
'All 20 full suite tests passed — updating full-suite-passed'
);
await github.rest.repos.createCommitStatus({
owner: context.repo.owner,
@@ -74,7 +89,6 @@ jobs:
sha,
state: 'success',
context: 'full-suite-passed',
description:
`All ${fullSuite.length} full suite tests passed`,
description: 'All 20 full suite tests passed',
});
}
.github/workflows/ci-scheduled-ssim.yml
+44
View File
@@ -0,0 +1,44 @@
name: Scheduled Full SSIM
on:
schedule:
- cron: "0 5 * * 0"
workflow_dispatch:
permissions:
contents: read
jobs:
trigger:
if: github.repository == 'hao-ai-lab/FastVideo'
runs-on: ubuntu-latest
steps:
- name: Trigger weekly full SSIM on Slinky Slurm
env:
BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
SOURCE_SHA: ${{ github.sha }}
SOURCE_BRANCH: ${{ github.event.repository.default_branch }}
BK_ORG: ${{ vars.BUILDKITE_ORG_SLUG }}
BK_PIPELINE: ${{ vars.BUILDKITE_PIPELINE_SLUG }}
run: |
set -euo pipefail
curl -sS --fail-with-body -X POST \
"https://api.buildkite.com/v2/organizations/${BK_ORG}/pipelines/${BK_PIPELINE}/builds" \
-H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
-H "Content-Type: application/json" \
--data-raw "$(jq -n \
--arg commit "$SOURCE_SHA" \
--arg branch "$SOURCE_BRANCH" \
'{
commit: $commit,
branch: $branch,
message: "Weekly full SSIM on Slinky Slurm",
ignore_pipeline_branch_filters: true,
env: {
TEST_SCOPE: "scheduled",
FULL_SUITE: "false",
TEST_TYPE: "ssim",
PR_NUMBER: "false",
PR_TITLE: "Scheduled full SSIM"
}
}')"
.github/workflows/ci-slash-commands.yml
+12 -44
View File
@@ -33,7 +33,6 @@ jobs:
core.setOutput('has_write', String(hasWrite));
- name: Add ready label and react
id: label
if: steps.perm.outputs.has_write == 'true'
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
with:
@@ -48,47 +47,6 @@ jobs:
comment_id: context.payload.comment.id,
content: 'rocket',
});
const { data: pr } = await github.rest.pulls.get({ owner, repo, pull_number: prNumber });
core.setOutput('pr_sha', pr.head.sha);
core.setOutput('pr_branch', pr.head.ref);
core.setOutput('pr_number', String(prNumber));
core.setOutput('pr_title', pr.title);
- name: Trigger Full Suite
if: steps.perm.outputs.has_write == 'true'
env:
BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
PR_SHA: ${{ steps.label.outputs.pr_sha }}
PR_BRANCH: ${{ steps.label.outputs.pr_branch }}
PR_NUMBER: ${{ steps.label.outputs.pr_number }}
PR_TITLE: ${{ steps.label.outputs.pr_title }}
BK_ORG: ${{ vars.BUILDKITE_ORG_SLUG }}
BK_PIPELINE: ${{ vars.BUILDKITE_PIPELINE_SLUG }}
run: |
curl -sS --fail-with-body -X POST \
"https://api.buildkite.com/v2/organizations/${BK_ORG}/pipelines/${BK_PIPELINE}/builds" \
-H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
-H "Content-Type: application/json" \
--data-raw "$(jq -n \
--arg commit "$PR_SHA" \
--arg branch "$PR_BRANCH" \
--arg message "Full Suite for PR #${PR_NUMBER} (via /merge)" \
--arg pr_title "$PR_TITLE" \
--argjson pr_id "$PR_NUMBER" \
'{
commit: $commit,
branch: $branch,
message: $message,
ignore_pipeline_branch_filters: true,
pull_request_id: $pr_id,
pull_request_base_branch: "main",
env: {
TEST_SCOPE: "full",
FULL_SUITE: "true",
PR_NUMBER: ($pr_id | tostring),
PR_TITLE: $pr_title
}
}')"
parse-command:
if: >-
@@ -129,7 +87,7 @@ jobs:
set -euo pipefail
TEST_NAME=$(echo "$COMMENT" | grep -oP '(?<=/test\s)\S+' | head -1 || true)
VALID="encoder vae transformer kernel unit dreamverse ssim golden-gate training lora-inference lora-training lora-extraction distillation self-forcing vsa vmoba performance api train-framework eval full fastcheck pre-commit"
VALID="encoder vae transformer kernel unit dreamverse ssim golden-gate training lora-inference lora-training lora-extraction distillation self-forcing vsa vmoba performance api train-framework eval unit-ci kernel-ci dreamverse-ci ssim-ci golden-gate-ci encoder-ci vae-ci transformer-ci lora-inference-ci lora-training-ci lora-extraction-ci training-ci distillation-ci self-forcing-ci vsa-ci vmoba-ci performance-ci api-ci train-framework-ci eval-ci full fastcheck pre-commit"
if [ -z "$TEST_NAME" ] || ! echo "$VALID" | grep -qw "$TEST_NAME"; then
echo "Unknown test: '$TEST_NAME'. Valid: $VALID"
exit 1
@@ -137,7 +95,17 @@ jobs:
declare -A MAP=(
[encoder]=encoder [vae]=vae [transformer]=transformer
[kernel]=kernel_tests [unit]=unit_test [dreamverse]=dreamverse_app
[kernel]=kernel_tests [unit]=unit_test [unit-ci]=unit_test_ci
[kernel-ci]=kernel_tests_ci [dreamverse-ci]=dreamverse_app_ci
[ssim-ci]=ssim_ci [vmoba-ci]=inference_vmoba_ci
[golden-gate-ci]=golden_gate_ci [training-ci]=training_ci
[encoder-ci]=encoder_ci [vae-ci]=vae_ci [transformer-ci]=transformer_ci
[lora-inference-ci]=inference_lora_ci [lora-training-ci]=training_lora_ci
[lora-extraction-ci]=lora_extraction_ci [distillation-ci]=distillation_dmd_ci
[self-forcing-ci]=self_forcing_ci [vsa-ci]=training_vsa_ci
[performance-ci]=performance_ci [api-ci]=api_server_ci
[train-framework-ci]=train_framework_ci [eval-ci]=eval_ci
[dreamverse]=dreamverse_app
[ssim]=ssim [golden-gate]=golden_gate [training]=training
[lora-inference]=inference_lora [lora-training]=training_lora
[lora-extraction]=lora_extraction
.github/workflows/ci-trigger-full-suite.yml
+66 -13
View File
@@ -1,4 +1,4 @@
name: Trigger Full Suite
name: Trigger Merge Gate
on:
pull_request_target:
@@ -10,7 +10,7 @@ permissions:
actions: read
concurrency:
group: full-suite-${{ github.event.pull_request.number }}
group: merge-gate-${{ github.event.pull_request.number }}
cancel-in-progress: false
jobs:
@@ -34,29 +34,72 @@ jobs:
});
const hasReady = pr.labels.some(l => l.name === 'ready');
core.setOutput('has_ready', String(hasReady));
if (!hasReady) core.info('No ready label — skipping Full Suite trigger.');
core.setOutput('changed_files', String(pr.changed_files));
if (!hasReady) core.info('No ready label — skipping merge-gate trigger.');
- name: Cancel previous Buildkite builds
if: steps.check.outputs.has_ready == 'true'
env:
BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
PR_BRANCH: ${{ github.event.pull_request.head.ref }}
PR_NUMBER: ${{ github.event.pull_request.number }}
run: |
# Find running builds for this branch with TEST_SCOPE=full and cancel them
builds=$(curl -sS -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
"https://api.buildkite.com/v2/organizations/${{ vars.BUILDKITE_ORG_SLUG }}/pipelines/${{ vars.BUILDKITE_PIPELINE_SLUG }}/builds?branch=${PR_BRANCH}&state=running,scheduled" \
| jq -r '.[] | select(try (.env.TEST_SCOPE == "full") catch false) | .number')
# Match both branch and PR number: forks can reuse the same branch name.
builds=$(curl -sS --get -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
--data-urlencode "branch=$PR_BRANCH" \
--data-urlencode "state=running,scheduled" \
"https://api.buildkite.com/v2/organizations/${{ vars.BUILDKITE_ORG_SLUG }}/pipelines/${{ vars.BUILDKITE_PIPELINE_SLUG }}/builds" \
| jq -r --arg pr_number "$PR_NUMBER" \
'.[] | select((.env.TEST_SCOPE? == "merge") and (.env.PR_NUMBER? == $pr_number)) | .number')
for build_num in $builds; do
echo "Cancelling Buildkite build #$build_num"
curl -sS -X PUT -H "Authorization: Bearer $BUILDKITE_API_TOKEN" \
"https://api.buildkite.com/v2/organizations/${{ vars.BUILDKITE_ORG_SLUG }}/pipelines/${{ vars.BUILDKITE_PIPELINE_SLUG }}/builds/${build_num}/cancel"
done
# Checks out the BASE branch (default for pull_request_target), so PR
# authors cannot tamper with the gate script.
- name: Checkout gate script
# Check out the immutable BASE SHA: pull_request_target must never run a
# planner or gate script from the untrusted PR head.
- name: Checkout trusted merge planner
if: steps.check.outputs.has_ready == 'true'
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ github.event.pull_request.base.sha }}
persist-credentials: false
- name: Collect changed paths
if: steps.check.outputs.has_ready == 'true'
env:
GH_TOKEN: ${{ github.token }}
PR_NUMBER: ${{ github.event.pull_request.number }}
EXPECTED_CHANGED_FILES: ${{ steps.check.outputs.changed_files }}
run: |
set -euo pipefail
changed_json="$RUNNER_TEMP/merge-changed-files.json"
changed_paths="$RUNNER_TEMP/merge-changed-paths.txt"
if gh api --paginate --slurp \
"repos/${GITHUB_REPOSITORY}/pulls/${PR_NUMBER}/files?per_page=100" \
> "$changed_json"; then
observed=$(jq '[.[][] | .filename] | unique | length' "$changed_json")
if [ "$observed" = "$EXPECTED_CHANGED_FILES" ]; then
jq -r '.[][] | .filename, (.previous_filename // empty)' "$changed_json" \
| sort -u > "$changed_paths"
else
echo "::warning::Changed-file API returned $observed of $EXPECTED_CHANGED_FILES paths; selecting all merge lanes."
echo '__FASTVIDEO_CI_PLAN_ALL__' > "$changed_paths"
fi
else
echo "::warning::Changed-file API failed; selecting all merge lanes."
echo '__FASTVIDEO_CI_PLAN_ALL__' > "$changed_paths"
fi
- name: Select minimal merge tests
id: plan
if: steps.check.outputs.has_ready == 'true'
run: |
python3 .github/scripts/plan_merge_ci.py \
--paths-file "$RUNNER_TEMP/merge-changed-paths.txt" \
--github-output "$GITHUB_OUTPUT" \
--summary-file "$GITHUB_STEP_SUMMARY"
- name: Wait for pre-commit and docs build
if: steps.check.outputs.has_ready == 'true'
@@ -66,7 +109,7 @@ jobs:
PR_NUMBER: ${{ github.event.pull_request.number }}
run: bash .github/scripts/gate_full_suite.sh
- name: Trigger Buildkite Full Suite
- name: Trigger Buildkite merge gate
if: steps.check.outputs.has_ready == 'true'
env:
BUILDKITE_API_TOKEN: ${{ secrets.BUILDKITE_API_TOKEN }}
@@ -76,6 +119,10 @@ jobs:
PR_TITLE: ${{ github.event.pull_request.title }}
BK_ORG: ${{ vars.BUILDKITE_ORG_SLUG }}
BK_PIPELINE: ${{ vars.BUILDKITE_PIPELINE_SLUG }}
MERGE_TEST_PLAN: ${{ steps.plan.outputs.merge_test_plan }}
MERGE_GOLDEN_TESTS: ${{ steps.plan.outputs.merge_golden_tests }}
MERGE_SSIM_TESTS: ${{ steps.plan.outputs.merge_ssim_tests }}
MERGE_PLAN_LABEL: ${{ steps.plan.outputs.merge_plan_label }}
run: |
curl -sS --fail-with-body -X POST \
"https://api.buildkite.com/v2/organizations/${BK_ORG}/pipelines/${BK_PIPELINE}/builds" \
@@ -84,8 +131,11 @@ jobs:
--data-raw "$(jq -n \
--arg commit "$PR_SHA" \
--arg branch "$PR_BRANCH" \
--arg message "Full Suite for PR #${PR_NUMBER}" \
--arg message "Merge gate [${MERGE_PLAN_LABEL}] for PR #${PR_NUMBER}" \
--arg pr_title "$PR_TITLE" \
--arg merge_test_plan "$MERGE_TEST_PLAN" \
--arg merge_golden_tests "$MERGE_GOLDEN_TESTS" \
--arg merge_ssim_tests "$MERGE_SSIM_TESTS" \
--argjson pr_id "$PR_NUMBER" \
'{
commit: $commit,
@@ -95,8 +145,11 @@ jobs:
pull_request_id: $pr_id,
pull_request_base_branch: "main",
env: {
TEST_SCOPE: "full",
TEST_SCOPE: "merge",
FULL_SUITE: "true",
MERGE_TEST_PLAN: $merge_test_plan,
MERGE_GOLDEN_TESTS: $merge_golden_tests,
MERGE_SSIM_TESTS: $merge_ssim_tests,
PR_NUMBER: ($pr_id | tostring),
PR_TITLE: $pr_title
}
.github/workflows/community-welcome.yml
+4 -4
View File
@@ -38,17 +38,17 @@ jobs:
**How our CI works:**
PRs run a two-tier CI system:
PRs run a three-tier CI system:
1. **Pre-commit** — formatting (yapf), linting (ruff), type checking (mypy). Runs immediately on every PR.
2. **Fastcheck** — core GPU tests (encoders, VAEs, transformers, kernels, unit tests). Runs automatically via Buildkite on relevant file changes (~10-15 min).
3. **Full Suite** — integration tests, training pipelines, SSIM regression. Runs only when a reviewer adds the `ready` label.
2. **Fastcheck** — six core GPU lanes run automatically via Buildkite (~10-15 min).
3. **Merge gate** — a reviewer adds `ready`; changed paths select only the relevant integration, training, golden, or SSIM coverage.
**Before your PR is reviewed:**
- [ ] `pre-commit run --all-files` passes locally
- [ ] You've added or updated tests for your changes
- [ ] The PR description explains what and why
If pre-commit fails, a bot comment will explain how to fix it. Fastcheck and Full Suite results appear in the Checks section below.
If pre-commit fails, a bot comment will explain how to fix it. Fastcheck and merge-gate results appear in the Checks section below.
**Useful links:**
- [Contributing Guide](https://hao-ai-lab.github.io/FastVideo/contributing/overview/)
.github/workflows/infra-build-image.yml
+27
View File
@@ -13,6 +13,11 @@ on:
required: false
default: false
type: boolean
build_ci_runner_image:
description: 'Build the ARM64 CUDA 13 CI runner image (sm_100)'
required: false
default: false
type: boolean
# Auto-rebuild the CUDA images when a repository-controlled image input
# changes on main. This includes the trusted SM89 kernel artifact's source,
# metadata/key helper, ABI dependency metadata, and build orchestration.
@@ -198,6 +203,28 @@ jobs:
docker buildx imagetools create "${TAG_ARGS[@]}" "${IMAGE_REFS[@]}"
docker buildx imagetools inspect "${TAGS[0]}"
# The CI runner is ARM64 like DGX Spark, but targets sm_100 rather than sm_121.
# Publish a single-architecture variant so the self-hosted CI runner can reuse
# the exact prebuilt kernel instead of compiling it in every job.
build-ci-runner-image:
if: ${{ (github.event_name == 'push' && github.repository == 'hao-ai-lab/FastVideo') || github.event.inputs.build_ci_runner_image == 'true' }}
uses: ./.github/workflows/_template-build-image.yml
with:
python_version: '3.12'
dockerfile_path: docker/Dockerfile
tag_suffix: py3.12-cuda13.0.0-sm100
runner: ubuntu-24.04-arm
architecture: arm64
build_args: |
PYTHON_VERSION=3.12
CUDA_VERSION=13.0.0
UV_TORCH_BACKEND=cu130
TORCH_CUDA_ARCH_LIST=10.0
CMAKE_BUILD_PARALLEL_LEVEL=1
FLASH_ATTN_WHEEL_TAG=cu130torch2.12
FLASH_ATTN_WHEEL_RELEASE_ARM64=https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.9.22
secrets: inherit
# Dreamverse matrix: {backend, UI} x {12.6.3, 13.0.0}, Python 3.12. Torch backend
# matches the base CUDA (cu126 / cu130). Keep these images amd64-only until the
# required FA4 dependency stack is available and validated on arm64.