[Kernel] Move sgl-kernel under sglang.kernels.aot (#32648)

This commit is contained in:
Xiaoyu Zhang
2026-07-29 17:25:00 +08:00
committed by GitHub
parent 1b9dfa14e6
commit c32c4ef79c
370 changed files with 300 additions and 269 deletions
+6 -3
View File
@@ -82,7 +82,9 @@ jobs:
- ".github/workflows/pr-gate.yml"
- ".github/actions/**"
- "python/pyproject.toml"
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/sglang/!(multimodal_gen|kernels)/**/!(*.md)"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**/!(*.md)"
- "scripts/ci/cuda/*"
- "scripts/ci/utils/*"
- "test/**/!(*.md)"
@@ -104,11 +106,12 @@ jobs:
- "test/registered/kernels/**"
# sglang.kernels is the migrated kernel namespace (RFC #29630 / #30044); the
# base-b-kernel suites import it directly, so kernel edits must run them.
- "python/sglang/kernels/**"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**"
sgl_kernel:
# Intentionally excludes ".github/workflows/pr-test-sgl-kernel.yml" —
# see API-side detector below for rationale.
- "sgl-kernel/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- "python/sglang/kernels/aot/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- name: Determine full-parallel mode
id: parallel-mode
@@ -100,19 +100,19 @@ jobs:
- name: Build wheel for Python ${{ matrix.python-version }} and CUDA ${{ matrix.cuda-version }}
run: |
cd sgl-kernel
cd python/sglang/kernels/aot
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}"
env:
USE_CCACHE: 1
- name: Verify wheel artifacts
run: |
ls -alh sgl-kernel/dist
ls -alh sgl-kernel/dist/*.whl
ls -alh python/sglang/kernels/aot/dist
ls -alh python/sglang/kernels/aot/dist/*.whl
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ inputs.arch_suffix }}
path: sgl-kernel/dist/*
path: python/sglang/kernels/aot/dist/*
if-no-files-found: error
+2 -2
View File
@@ -108,7 +108,7 @@ jobs:
if: ${{ fromJson(inputs.check_changes).sgl_kernel == 'true' && steps.rc.outputs.artifact_version == 'v4' }}
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -116,7 +116,7 @@ jobs:
if: ${{ fromJson(inputs.check_changes).sgl_kernel == 'true' && steps.rc.outputs.artifact_version == 'v6' }}
uses: actions/download-artifact@v6
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
+16 -16
View File
@@ -186,17 +186,17 @@ jobs:
diffusion-ci/consistency_gt/official_generated/case_map.json
sparse-checkout-cone-mode: false
- name: Prepare sgl-kernel/dist for prebuilt wheel
- name: Prepare AOT dist for prebuilt wheel
if: inputs.kernel_artifact_run_id != ''
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download prebuilt sgl-kernel wheel
if: inputs.kernel_artifact_run_id != ''
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
name: wheel-python3.10-cuda13.0
run-id: ${{ inputs.kernel_artifact_run_id }}
@@ -382,17 +382,17 @@ jobs:
with:
ref: ${{ inputs.ref || github.ref }}
- name: Prepare sgl-kernel/dist for prebuilt wheel
- name: Prepare AOT dist for prebuilt wheel
if: inputs.kernel_artifact_run_id != ''
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download prebuilt sgl-kernel wheel
if: inputs.kernel_artifact_run_id != ''
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
name: wheel-python3.10-cuda13.0
run-id: ${{ inputs.kernel_artifact_run_id }}
@@ -457,17 +457,17 @@ jobs:
with:
ref: ${{ inputs.ref || github.ref }}
- name: Prepare sgl-kernel/dist for prebuilt wheel
- name: Prepare AOT dist for prebuilt wheel
if: inputs.kernel_artifact_run_id != ''
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download prebuilt sgl-kernel wheel
if: inputs.kernel_artifact_run_id != ''
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
name: wheel-python3.10-cuda13.0
run-id: ${{ inputs.kernel_artifact_run_id }}
@@ -532,17 +532,17 @@ jobs:
with:
ref: ${{ inputs.ref || github.ref }}
- name: Prepare sgl-kernel/dist for prebuilt wheel
- name: Prepare AOT dist for prebuilt wheel
if: inputs.kernel_artifact_run_id != ''
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download prebuilt sgl-kernel wheel
if: inputs.kernel_artifact_run_id != ''
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
name: wheel-python3.10-cuda13.0
run-id: ${{ inputs.kernel_artifact_run_id }}
+1 -1
View File
@@ -59,7 +59,7 @@ jobs:
- name: Run sgl-kernel clang-format checks
uses: DoozyX/clang-format-lint-action@v0.20
with:
source: sgl-kernel
source: python/sglang/kernels/aot
extensions: h,c,cpp,hpp,cu,cuh,cc
clangFormatVersion: 20
style: file
+1 -1
View File
@@ -132,7 +132,7 @@ jobs:
image_tag: ${{ steps.build.outputs.image_tag }}
steps:
# Self-hosted runners retain the workspace across jobs. Prior `docker buildx`
# runs on this node leave root-owned build artifacts (e.g. sgl-kernel/build/)
# runs on this node leave root-owned build artifacts (e.g. python/sglang/kernels/aot/build/)
# that actions/checkout cannot remove, causing EACCES on rmdir. Wipe them
# via a throwaway root container before checkout recreates the workspace.
- name: Clean workspace (remove root-owned files from prior runs)
+5 -5
View File
@@ -74,11 +74,11 @@ jobs:
if: steps.gate.outputs.run_job == 'true'
timeout-minutes: 30
run: |
pytest sgl-kernel/tests/test_per_token_quant_fp8.py
pytest sgl-kernel/tests/speculative/test_eagle_utils.py
pytest sgl-kernel/tests/speculative/test_ngram_utils.py
pytest sgl-kernel/tests/speculative/test_speculative_sampling.py
pytest sgl-kernel/tests/test_torch_defaults_reset.py
pytest python/sglang/kernels/aot/tests/test_per_token_quant_fp8.py
pytest python/sglang/kernels/aot/tests/speculative/test_eagle_utils.py
pytest python/sglang/kernels/aot/tests/speculative/test_ngram_utils.py
pytest python/sglang/kernels/aot/tests/speculative/test_speculative_sampling.py
pytest python/sglang/kernels/aot/tests/test_torch_defaults_reset.py
# ==================== General: multimodal layer ====================
nightly-test-musa-general-multimodal-layer:
+20 -17
View File
@@ -15,7 +15,7 @@ on:
# - "python/**"
# - "scripts/ci/**"
# - "test/**"
# - "sgl-kernel/**"
# - "python/sglang/kernels/aot/**"
# - ".github/workflows/pr-test-amd-rocm720.yml"
# - "docker/rocm.Dockerfile"
# pull_request:
@@ -23,7 +23,7 @@ on:
# - "python/**"
# - "scripts/ci/**"
# - "test/**"
# - "sgl-kernel/**"
# - "python/sglang/kernels/aot/**"
# - ".github/workflows/pr-test-amd-rocm720.yml"
# - "docker/rocm.Dockerfile"
workflow_dispatch:
@@ -187,7 +187,9 @@ jobs:
with:
filters: |
main_package:
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/sglang/!(multimodal_gen|kernels)/**/!(*.md)"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**/!(*.md)"
- "python/pyproject_rocm.toml"
- "python/pyproject_other.toml"
- "scripts/ci/amd/*"
@@ -195,10 +197,11 @@ jobs:
- "test/**/!(*.md)"
- ".github/workflows/pr-test-amd-rocm720.yml"
sgl_kernel:
- "sgl-kernel/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- "python/sglang/kernels/aot/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- ".github/workflows/pr-test-amd-rocm720.yml"
jit_kernel:
- "python/sglang/kernels/**"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**"
- "test/registered/kernels/**"
- ".github/workflows/pr-test-amd-rocm720.yml"
multimodal_gen:
@@ -268,15 +271,15 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_align.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_softmax.py
docker exec -w /sglang-checkout/sgl-kernel/tests/speculative ci_sglang python3 -m pytest test_eagle_utils.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_apply_token_bitmask_inplace.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_activation.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_topk.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_kvcacheio.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_sigmoid.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_torch_defaults_reset.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_moe_align.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_moe_topk_softmax.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests/speculative ci_sglang python3 -m pytest test_eagle_utils.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_apply_token_bitmask_inplace.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_activation.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_topk.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_kvcacheio.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_moe_topk_sigmoid.py
docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_torch_defaults_reset.py
sgl-kernel-unit-test-2-gpu-amd-rocm720:
needs: [check-changes]
@@ -657,7 +660,7 @@ jobs:
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
@@ -797,7 +800,7 @@ jobs:
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
@@ -934,7 +937,7 @@ jobs:
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
+19 -16
View File
@@ -11,7 +11,7 @@ on:
- "python/**"
- "scripts/ci/**"
- "test/**"
- "sgl-kernel/**"
- "python/sglang/kernels/aot/**"
- ".github/workflows/pr-test-amd.yml"
- "docker/rocm.Dockerfile"
workflow_dispatch:
@@ -175,7 +175,9 @@ jobs:
with:
filters: |
main_package:
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/sglang/!(multimodal_gen|kernels)/**/!(*.md)"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**/!(*.md)"
- "python/pyproject_rocm.toml"
- "python/pyproject_other.toml"
- "scripts/ci/amd/*"
@@ -183,10 +185,11 @@ jobs:
- "test/**/!(*.md)"
- ".github/workflows/pr-test-amd.yml"
sgl_kernel:
- "sgl-kernel/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- "python/sglang/kernels/aot/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- ".github/workflows/pr-test-amd.yml"
jit_kernel:
- "python/sglang/kernels/**"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**"
- "test/registered/kernels/**"
- ".github/workflows/pr-test-amd.yml"
multimodal_gen:
@@ -266,15 +269,15 @@ jobs:
"$@"
fi
}
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_align.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_softmax.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests/speculative ci_sglang python3 -m pytest test_eagle_utils.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_apply_token_bitmask_inplace.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_activation.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_topk.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_kvcacheio.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_sigmoid.py
run_pytest docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_torch_defaults_reset.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_moe_align.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_moe_topk_softmax.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests/speculative ci_sglang python3 -m pytest test_eagle_utils.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_apply_token_bitmask_inplace.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_activation.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_topk.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_kvcacheio.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_moe_topk_sigmoid.py
run_pytest docker exec -w /sglang-checkout/python/sglang/kernels/aot/tests ci_sglang python3 -m pytest test_torch_defaults_reset.py
exit $failures
sgl-kernel-unit-test-2-gpu-amd:
@@ -681,7 +684,7 @@ jobs:
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
@@ -821,7 +824,7 @@ jobs:
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
@@ -960,7 +963,7 @@ jobs:
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
+1 -1
View File
@@ -55,7 +55,7 @@ jobs:
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/pyproject_cpu.toml"
- "test/**/!(*.md)"
- "sgl-kernel/**/*.!(md|txt)"
- "python/sglang/kernels/aot/**/*.!(md|txt)"
- ".github/workflows/pr-test-arm64.yml"
- "docker/arm64.Dockerfile"
+12 -12
View File
@@ -56,14 +56,14 @@ jobs:
- name: Cleanup
if: inputs.sgl_kernel == 'true'
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda13.0
@@ -94,14 +94,14 @@ jobs:
- name: Cleanup
if: inputs.sgl_kernel == 'true'
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda13.0
@@ -134,14 +134,14 @@ jobs:
- name: Cleanup
if: inputs.sgl_kernel == 'true'
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda13.0
@@ -174,14 +174,14 @@ jobs:
- name: Cleanup
if: inputs.sgl_kernel == 'true'
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda13.0
+4 -2
View File
@@ -43,12 +43,14 @@ jobs:
base: main
filters: |
main_package:
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/sglang/!(multimodal_gen|kernels)/**/!(*.md)"
- "python/sglang/kernels/!(*.md)"
- "python/sglang/kernels/!(aot)/**/!(*.md)"
- "python/pyproject_other.toml"
- "test/**/!(*.md)"
- ".github/workflows/pr-test-mlx.yml"
sgl_kernel:
- "sgl-kernel/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- "python/sglang/kernels/aot/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- ".github/workflows/pr-test-mlx.yml"
# ==================== PR Gate ==================== #
+7 -7
View File
@@ -98,7 +98,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -164,7 +164,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -227,7 +227,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -289,7 +289,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -356,7 +356,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -401,7 +401,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -455,7 +455,7 @@ jobs:
if: inputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
+6 -6
View File
@@ -83,7 +83,7 @@ jobs:
- "python/sglang/multimodal_gen/test/server/musa/**"
sgl_kernel:
- ".github/workflows/pr-test-musa.yml"
- "sgl-kernel/csrc/musa/**"
- "python/sglang/kernels/aot/csrc/musa/**"
# ==================== PR Gate ==================== #
pr-gate:
@@ -217,11 +217,11 @@ jobs:
- name: Run sgl-kernel test
timeout-minutes: 20
run: |
pytest sgl-kernel/tests/test_per_token_quant_fp8.py
pytest sgl-kernel/tests/speculative/test_eagle_utils.py
pytest sgl-kernel/tests/speculative/test_ngram_utils.py
pytest sgl-kernel/tests/speculative/test_speculative_sampling.py
pytest sgl-kernel/tests/test_torch_defaults_reset.py
pytest python/sglang/kernels/aot/tests/test_per_token_quant_fp8.py
pytest python/sglang/kernels/aot/tests/speculative/test_eagle_utils.py
pytest python/sglang/kernels/aot/tests/speculative/test_ngram_utils.py
pytest python/sglang/kernels/aot/tests/speculative/test_speculative_sampling.py
pytest python/sglang/kernels/aot/tests/test_torch_defaults_reset.py
pr-test-musa-finish:
+16 -16
View File
@@ -44,13 +44,13 @@ jobs:
- name: Cleanup
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -62,7 +62,7 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
cd sgl-kernel
cd python/sglang/kernels/aot
pytest tests/
sgl-kernel-benchmark-test:
@@ -79,13 +79,13 @@ jobs:
- name: Cleanup
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -97,7 +97,7 @@ jobs:
- name: Run benchmark tests
timeout-minutes: 45
run: |
cd sgl-kernel/benchmark
cd python/sglang/kernels/aot/benchmark
echo "Running sgl-kernel benchmark tests in CI mode..."
echo "CI environment variable: $CI"
@@ -126,13 +126,13 @@ jobs:
- name: Cleanup
run: |
ls -alh sgl-kernel/dist || true
rm -rf sgl-kernel/dist/* || true
ls -alh python/sglang/kernels/aot/dist || true
rm -rf python/sglang/kernels/aot/dist/* || true
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda*
@@ -144,7 +144,7 @@ jobs:
- name: Run sgl-kernel unit tests on B200
timeout-minutes: 30
run: |
cd sgl-kernel
cd python/sglang/kernels/aot
pytest tests/
# Adding a single CUDA13 build-and-run check for the kernel
@@ -157,13 +157,13 @@ jobs:
# - name: Cleanup
# run: |
# ls -alh sgl-kernel/dist || true
# rm -rf sgl-kernel/dist/* || true
# ls -alh python/sglang/kernels/aot/dist || true
# rm -rf python/sglang/kernels/aot/dist/* || true
# - name: Download CUDA 13.0 artifacts
# uses: actions/download-artifact@v4
# with:
# path: sgl-kernel/dist/
# path: python/sglang/kernels/aot/dist/
# merge-multiple: true
# pattern: wheel-python3.10-cuda*
@@ -174,5 +174,5 @@ jobs:
# - name: Run kernel unit tests
# timeout-minutes: 30
# run: |
# cd sgl-kernel
# cd python/sglang/kernels/aot
# pytest tests/
+1 -1
View File
@@ -66,7 +66,7 @@ jobs:
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/pyproject_cpu.toml"
- "test/**/!(*.md)"
- "sgl-kernel/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- "python/sglang/kernels/aot/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- ".github/workflows/pr-test-xeon.yml"
- "docker/xeon.Dockerfile"
+1 -1
View File
@@ -57,7 +57,7 @@ jobs:
- "python/sglang/!(multimodal_gen)/**/!(*.md)"
- "python/pyproject_xpu.toml"
- "test/**/!(*.md)"
- "sgl-kernel/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- "python/sglang/kernels/aot/**/!(*.md|THIRDPARTYNOTICES.txt|LICENSE)"
- ".github/workflows/pr-test-xpu.yml"
- "docker/xpu.Dockerfile"
+32 -32
View File
@@ -5,7 +5,7 @@ on:
branches:
- main
paths:
- sgl-kernel/python/sgl_kernel/version.py
- python/sglang/kernels/aot/python/sgl_kernel/version.py
workflow_dispatch:
inputs:
target:
@@ -54,7 +54,7 @@ jobs:
runs-on: ${{ matrix.runner }}
steps:
# Self-hosted build nodes retain the workspace across jobs. Prior builds
# leave root-owned artifacts under sgl-kernel/build/ that actions/checkout
# leave root-owned artifacts under python/sglang/kernels/aot/build/ that actions/checkout
# cannot remove, causing EACCES on rmdir. Wipe them via a throwaway root
# container before checkout recreates the workspace.
- name: Clean workspace (remove root-owned files from prior runs)
@@ -74,7 +74,7 @@ jobs:
- name: Build wheels
run: |
cd sgl-kernel
cd python/sglang/kernels/aot
chmod +x ./build.sh
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
env:
@@ -85,7 +85,7 @@ jobs:
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
path: sgl-kernel/dist/*
path: python/sglang/kernels/aot/dist/*
release-cu129:
needs: build-cu129-matrix
@@ -98,7 +98,7 @@ jobs:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-*
@@ -106,7 +106,7 @@ jobs:
id: set_tag_name
run: |
if [ -z "${{ inputs.tag_name }}" ]; then
TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
TAG_NAME="v$(cat python/sglang/kernels/aot/python/sgl_kernel/version.py | cut -d'"' -f2)"
echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
else
echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
@@ -119,7 +119,7 @@ jobs:
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
sgl-kernel/dist/*
python/sglang/kernels/aot/dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
@@ -155,7 +155,7 @@ jobs:
runs-on: ${{ matrix.runner }}
steps:
# Self-hosted build nodes retain the workspace across jobs. Prior builds
# leave root-owned artifacts under sgl-kernel/build/ that actions/checkout
# leave root-owned artifacts under python/sglang/kernels/aot/build/ that actions/checkout
# cannot remove, causing EACCES on rmdir. Wipe them via a throwaway root
# container before checkout recreates the workspace.
- name: Clean workspace (remove root-owned files from prior runs)
@@ -175,7 +175,7 @@ jobs:
- name: Build wheels
run: |
cd sgl-kernel
cd python/sglang/kernels/aot
chmod +x ./build.sh
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
env:
@@ -183,7 +183,7 @@ jobs:
NVCC_THREADS: 8
- name: Strip +cu130 local version for PyPI upload
working-directory: sgl-kernel
working-directory: python/sglang/kernels/aot
run: |
set -eux
pip install wheel
@@ -208,7 +208,7 @@ jobs:
ls -lh dist-pypi/
- name: Upload to PyPI
working-directory: sgl-kernel
working-directory: python/sglang/kernels/aot
run: |
pip install twine
python3 -m twine upload --skip-existing dist-pypi/* -u __token__ -p ${{ secrets.PYPI_TOKEN_SGLANG_KERNEL }}
@@ -217,7 +217,7 @@ jobs:
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
path: sgl-kernel/dist/*
path: python/sglang/kernels/aot/dist/*
release-cu130:
needs: build-cu130-matrix
@@ -230,7 +230,7 @@ jobs:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-*
@@ -238,7 +238,7 @@ jobs:
id: set_tag_name
run: |
if [ -z "${{ inputs.tag_name }}" ]; then
TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
TAG_NAME="v$(cat python/sglang/kernels/aot/python/sgl_kernel/version.py | cut -d'"' -f2)"
echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
else
echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
@@ -251,7 +251,7 @@ jobs:
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
sgl-kernel/dist/*
python/sglang/kernels/aot/dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
@@ -281,7 +281,7 @@ jobs:
rocm-version: ["700", "720"]
steps:
# Self-hosted build nodes retain the workspace across jobs. Prior builds
# leave root-owned artifacts under sgl-kernel/build/ that actions/checkout
# leave root-owned artifacts under python/sglang/kernels/aot/build/ that actions/checkout
# cannot remove, causing EACCES on rmdir. Wipe them via a throwaway root
# container before checkout recreates the workspace.
- name: Clean workspace (remove root-owned files from prior runs)
@@ -301,8 +301,8 @@ jobs:
- name: Build wheels
run: |
cp 3rdparty/amd/wheel/sgl-kernel/* sgl-kernel/
cd sgl-kernel
cp 3rdparty/amd/wheel/sgl-kernel/* python/sglang/kernels/aot/
cd python/sglang/kernels/aot
chmod +x ./build_rocm.sh
./build_rocm.sh "${{ matrix.rocm-version }}"
@@ -310,7 +310,7 @@ jobs:
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-rocm${{ matrix.rocm-version }}
path: sgl-kernel/dist/*
path: python/sglang/kernels/aot/dist/*
release-rocm700:
needs: build-rocm-matrix
@@ -323,7 +323,7 @@ jobs:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-*-rocm700
@@ -331,7 +331,7 @@ jobs:
id: set_tag_name
run: |
if [ -z "${{ inputs.tag_name }}" ]; then
TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
TAG_NAME="v$(cat python/sglang/kernels/aot/python/sgl_kernel/version.py | cut -d'"' -f2)"
echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
else
echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
@@ -344,7 +344,7 @@ jobs:
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
sgl-kernel/dist/*
python/sglang/kernels/aot/dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
@@ -374,7 +374,7 @@ jobs:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-*-rocm720
@@ -382,7 +382,7 @@ jobs:
id: set_tag_name
run: |
if [ -z "${{ inputs.tag_name }}" ]; then
TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
TAG_NAME="v$(cat python/sglang/kernels/aot/python/sgl_kernel/version.py | cut -d'"' -f2)"
echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
else
echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
@@ -395,7 +395,7 @@ jobs:
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
sgl-kernel/dist/*
python/sglang/kernels/aot/dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
@@ -425,7 +425,7 @@ jobs:
musa-version: ["43"]
steps:
# Self-hosted build nodes retain the workspace across jobs. Prior builds
# leave root-owned artifacts under sgl-kernel/build/ that actions/checkout
# leave root-owned artifacts under python/sglang/kernels/aot/build/ that actions/checkout
# cannot remove, causing EACCES on rmdir. Wipe them via a throwaway root
# container before checkout recreates the workspace.
- name: Clean workspace (remove root-owned files from prior runs)
@@ -451,19 +451,19 @@ jobs:
- name: Build wheels
run: |
cd sgl-kernel
cd python/sglang/kernels/aot
mv pyproject_musa.toml pyproject.toml
python setup_musa.py sdist bdist_wheel
- name: Rename MUSA wheels
run: |
bash scripts/ci/musa/rename_wheels_musa.sh ${{ matrix.musa-version }} sgl-kernel/dist
bash scripts/ci/musa/rename_wheels_musa.sh ${{ matrix.musa-version }} python/sglang/kernels/aot/dist
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-musa${{ matrix.musa-version }}
path: sgl-kernel/dist/*
path: python/sglang/kernels/aot/dist/*
release-musa43:
needs: build-musa43
@@ -474,7 +474,7 @@ jobs:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-*
@@ -482,7 +482,7 @@ jobs:
id: set_tag_name
run: |
if [ -z "${{ inputs.tag_name }}" ]; then
TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
TAG_NAME="v$(cat python/sglang/kernels/aot/python/sgl_kernel/version.py | cut -d'"' -f2)"
echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
else
echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
@@ -495,7 +495,7 @@ jobs:
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
sgl-kernel/dist/*
python/sglang/kernels/aot/dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl