fix(build): suppress MLX folding warning after flags #154
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Triton AOT vendored-artifact sync. | |
| # | |
| # Two jobs: | |
| # 1. drift-check (GitHub-hosted, no GPU): pure sha256 compare of | |
| # triton_kernels/*.py vs every vendored MANIFEST. Runs on any push/PR that | |
| # touches the kernels, the vendored tree, or the AOT cmake. FAILS on drift, | |
| # so a kernel change cannot merge while shipping stale cubins. | |
| # 2. regen-pr (SELF-HOSTED GPU runner, label [self-hosted, gpu]): actually | |
| # reruns scripts/regen-triton-aot.sh and opens a sync PR with the refreshed | |
| # artifacts, then executes them on CUDA. Generation is target-pinned; runtime | |
| # validation requires the self-hosted GPU runner (e.g. dgx.casa). | |
| # Trigger manually (workflow_dispatch) or via the weekly schedule; it only | |
| # opens a PR when the drift check says the tree is stale. | |
| name: triton-aot-sync | |
| on: | |
| push: | |
| branches: [main] | |
| paths: | |
| - '.github/workflows/triton-aot-sync.yml' | |
| - 'CMakeLists.txt' | |
| - 'triton_kernels/**' | |
| - 'src/vt/cuda/triton_aot_vendored/**' | |
| - 'cmake/TritonAOT.cmake' | |
| - 'cmake/TritonAOTKernels.cmake' | |
| - 'cmake/DumpTritonAOTContract.cmake' | |
| - 'scripts/regen-triton-aot.sh' | |
| - 'scripts/check-triton-aot-drift.sh' | |
| - 'scripts/triton-aot-compile.py' | |
| - 'tests/scripts/test_triton_aot_drift.sh' | |
| pull_request: | |
| paths: | |
| - '.github/workflows/triton-aot-sync.yml' | |
| - 'CMakeLists.txt' | |
| - 'triton_kernels/**' | |
| - 'src/vt/cuda/triton_aot_vendored/**' | |
| - 'cmake/TritonAOT.cmake' | |
| - 'cmake/TritonAOTKernels.cmake' | |
| - 'cmake/DumpTritonAOTContract.cmake' | |
| - 'scripts/regen-triton-aot.sh' | |
| - 'scripts/check-triton-aot-drift.sh' | |
| - 'scripts/triton-aot-compile.py' | |
| - 'tests/scripts/test_triton_aot_drift.sh' | |
| schedule: | |
| - cron: '17 5 * * 1' # weekly drift audit (Mon 05:17 UTC) | |
| workflow_dispatch: {} | |
| permissions: | |
| contents: write | |
| pull-requests: write | |
| jobs: | |
| drift-check: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Check vendored Triton AOT artifacts vs kernel sources | |
| run: bash scripts/check-triton-aot-drift.sh | |
| regen-pr: | |
| # Only meaningful with a GPU runner registered; scheduled/manual only so | |
| # ordinary pushes never queue on a runner that may not exist. | |
| if: github.event_name == 'workflow_dispatch' || github.event_name == 'schedule' | |
| runs-on: [self-hosted, gpu] | |
| needs: [] | |
| timeout-minutes: 60 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Skip if already in sync | |
| id: drift | |
| run: | | |
| if bash scripts/check-triton-aot-drift.sh; then | |
| echo "stale=false" >> "$GITHUB_OUTPUT" | |
| else | |
| echo "stale=true" >> "$GITHUB_OUTPUT" | |
| fi | |
| - name: Regenerate vendored artifacts | |
| if: steps.drift.outputs.stale == 'true' | |
| run: flock -w 7200 /tmp/gpu bash scripts/regen-triton-aot.sh | |
| - name: Verify regenerated artifact contract and vendored consumer | |
| if: steps.drift.outputs.stale == 'true' | |
| run: | | |
| bash scripts/check-triton-aot-drift.sh | |
| cmake -S . -B build-triton-aot-consumer \ | |
| -DVLLM_CPP_CUDA=ON \ | |
| -DVLLM_CPP_CUDA_ARCHITECTURES=121a \ | |
| -DVLLM_CPP_TRITON=ON \ | |
| -DVLLM_CPP_TRITON_REGEN=OFF \ | |
| -DVLLM_CPP_BUILD_TESTS=ON \ | |
| -DVLLM_CPP_BUILD_EXAMPLES=OFF \ | |
| -DVLLM_CPP_SERVER=OFF | |
| cmake --build build-triton-aot-consumer --target vllm test_ops_gdn -j2 | |
| flock -w 7200 /tmp/gpu \ | |
| build-triton-aot-consumer/tests/test_ops_gdn | |
| - name: Open sync PR | |
| if: steps.drift.outputs.stale == 'true' | |
| env: | |
| GH_TOKEN: ${{ github.token }} | |
| run: | | |
| set -euo pipefail | |
| git config user.name "triton-aot-sync[bot]" | |
| git config user.email "[email protected]" | |
| branch="sync/triton-aot-$(date -u +%Y%m%d-%H%M)" | |
| git checkout -b "$branch" | |
| git add src/vt/cuda/triton_aot_vendored/ | |
| git commit -F - <<'MSG' | |
| build: sync vendored Triton AOT artifacts with triton_kernels sources (automated regen) | |
| Automated regen via scripts/regen-triton-aot.sh after drift was detected by | |
| scripts/check-triton-aot-drift.sh. Review the MANIFEST + artifact diff, then | |
| merge; CI's drift-check gates that the result is coherent. | |
| FOLLOWING_AGENTS_PROTOCOL | |
| Assisted-by: triton-aot-sync:workflow [GitHubActions] | |
| MSG | |
| git push origin "$branch" | |
| gh pr create --base main --head "$branch" \ | |
| --title "build: sync vendored Triton AOT artifacts (automated regen)" \ | |
| --body "Automated regen of \`src/vt/cuda/triton_aot_vendored/\` after \`scripts/check-triton-aot-drift.sh\` detected drift vs \`triton_kernels/*.py\`. Review the MANIFEST diff (triton/ptxas/toolkit pins + per-kernel source hashes) and the artifact churn, then merge. Generated on a self-hosted GPU runner via \`scripts/regen-triton-aot.sh\`." |