[ci] allow manual label to trigger ci in rust, change ci order (#14016)
This commit is contained in:
Simo Lin
@@ -21,12 +21,8 @@ concurrency:
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
call-gate:
|
||||
uses: ./.github/workflows/pr-gate.yml
|
||||
secrets: inherit
|
||||
# =============================================== check changes ====================================================
|
||||
check-changes:
|
||||
needs: [call-gate]
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
main_package: ${{ steps.filter.outputs.main_package }}
|
||||
@@ -67,10 +63,20 @@ jobs:
|
||||
echo "| multimodal_gen | ${{ steps.filter.outputs.multimodal_gen }} |"
|
||||
} >> $GITHUB_STEP_SUMMARY
|
||||
|
||||
# =============================================== PR Gate ====================================================
|
||||
call-gate:
|
||||
needs: check-changes
|
||||
if: |
|
||||
needs.check-changes.outputs.main_package == 'true' ||
|
||||
needs.check-changes.outputs.sgl_kernel == 'true' ||
|
||||
needs.check-changes.outputs.multimodal_gen == 'true'
|
||||
uses: ./.github/workflows/pr-gate.yml
|
||||
secrets: inherit
|
||||
|
||||
# =============================================== sgl-kernel ====================================================
|
||||
|
||||
sgl-kernel-build-wheels:
|
||||
needs: [check-changes]
|
||||
needs: [check-changes, call-gate]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: x64-kernel-build-node
|
||||
strategy:
|
||||
@@ -110,7 +116,7 @@ jobs:
|
||||
path: sgl-kernel/dist/*
|
||||
|
||||
sgl-kernel-build-wheels-arm:
|
||||
needs: [check-changes]
|
||||
needs: [check-changes, call-gate]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: arm-kernel-build-node
|
||||
strategy:
|
||||
@@ -151,7 +157,7 @@ jobs:
|
||||
path: sgl-kernel/dist/*
|
||||
|
||||
sgl-kernel-unit-test:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
@@ -182,7 +188,7 @@ jobs:
|
||||
pytest tests/
|
||||
|
||||
sgl-kernel-mla-test:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
@@ -213,7 +219,7 @@ jobs:
|
||||
python3 test_mla_deepseek_v3.py
|
||||
|
||||
sgl-kernel-benchmark-test:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
@@ -321,7 +327,7 @@ jobs:
|
||||
# =============================================== primary ====================================================
|
||||
|
||||
stage-a-test-1:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -353,7 +359,7 @@ jobs:
|
||||
|
||||
|
||||
multimodal-gen-test-1-gpu:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: (always() && !failure() && !cancelled()) && needs.check-changes.outputs.multimodal_gen == 'true'
|
||||
runs-on: 1-gpu-runner
|
||||
strategy:
|
||||
@@ -391,7 +397,7 @@ jobs:
|
||||
|
||||
|
||||
multimodal-gen-test-2-gpu:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: (always() && !failure() && !cancelled()) && needs.check-changes.outputs.multimodal_gen == 'true'
|
||||
runs-on: 2-gpu-runner
|
||||
strategy:
|
||||
@@ -429,7 +435,7 @@ jobs:
|
||||
--total-partitions 2
|
||||
|
||||
quantization-test:
|
||||
needs: [check-changes, stage-a-test-1]
|
||||
needs: [check-changes, call-gate, stage-a-test-1]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -456,7 +462,7 @@ jobs:
|
||||
python3 run_suite.py --suite quantization_test
|
||||
|
||||
unit-test-backend-1-gpu:
|
||||
needs: [check-changes, stage-a-test-1]
|
||||
needs: [check-changes, call-gate, stage-a-test-1]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -490,7 +496,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 15
|
||||
|
||||
unit-test-backend-2-gpu:
|
||||
needs: [check-changes, unit-test-backend-1-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-1-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 2-gpu-runner
|
||||
@@ -523,7 +529,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-2-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
|
||||
|
||||
unit-test-backend-4-gpu:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-h100
|
||||
@@ -556,7 +562,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
|
||||
|
||||
unit-test-backend-8-gpu-h200:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 8-gpu-h200
|
||||
@@ -589,7 +595,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3
|
||||
|
||||
unit-test-backend-8-gpu-h20:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 8-gpu-h20
|
||||
@@ -623,7 +629,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
|
||||
|
||||
performance-test-1-gpu-part-1:
|
||||
needs: [check-changes, stage-a-test-1]
|
||||
needs: [check-changes, call-gate, stage-a-test-1]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -684,7 +690,7 @@ jobs:
|
||||
python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency_with_concurrent_adapter_updates
|
||||
|
||||
performance-test-1-gpu-part-2:
|
||||
needs: [check-changes, stage-a-test-1]
|
||||
needs: [check-changes, call-gate, stage-a-test-1]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -737,7 +743,7 @@ jobs:
|
||||
python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency
|
||||
|
||||
performance-test-1-gpu-part-3:
|
||||
needs: [check-changes, stage-a-test-1]
|
||||
needs: [check-changes, call-gate, stage-a-test-1]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -784,7 +790,7 @@ jobs:
|
||||
python3 -m unittest test_bench_serving.TestBenchServing.test_embeddings_api_batch_scaling
|
||||
|
||||
performance-test-2-gpu:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 2-gpu-runner
|
||||
@@ -843,7 +849,7 @@ jobs:
|
||||
python3 -m unittest test_bench_serving.TestBenchServing.test_pp_long_context_prefill
|
||||
|
||||
accuracy-test-1-gpu:
|
||||
needs: [check-changes, stage-a-test-1]
|
||||
needs: [check-changes, call-gate, stage-a-test-1]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
@@ -875,7 +881,7 @@ jobs:
|
||||
python3 test_eval_accuracy_large.py
|
||||
|
||||
accuracy-test-2-gpu:
|
||||
needs: [check-changes, accuracy-test-1-gpu]
|
||||
needs: [check-changes, call-gate, accuracy-test-1-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 2-gpu-runner
|
||||
@@ -907,7 +913,7 @@ jobs:
|
||||
python3 test_moe_eval_accuracy_large.py
|
||||
|
||||
unit-test-deepep-4-gpu:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-h100
|
||||
@@ -936,7 +942,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-4-gpu-deepep
|
||||
|
||||
unit-test-deepep-8-gpu:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 8-gpu-h200
|
||||
@@ -965,7 +971,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-8-gpu-h200-deepep
|
||||
|
||||
unit-test-backend-4-gpu-b200:
|
||||
needs: [check-changes, unit-test-backend-2-gpu]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-b200
|
||||
@@ -999,7 +1005,7 @@ jobs:
|
||||
python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800
|
||||
|
||||
unit-test-backend-4-gpu-gb200:
|
||||
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
|
||||
needs: [check-changes, call-gate, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-gb200
|
||||
|
||||
Reference in New Issue
Block a user