minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[CI] Fix CUDA workflow's dependency. (#13568)

Browse Source
This commit is contained in:
Liangsheng Yin
2025-11-19 19:06:42 +08:00
committed by GitHub
parent e197bef5ce
commit 97ba2c2d1e
1 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test.yml
+16 -16
View File
@@ -317,8 +317,8 @@ jobs:
multimodal-gen-test: multimodal-gen-test:
needs: [check-changes, stage-a-test-1, sgl-kernel-build-wheels] needs: [check-changes, sgl-kernel-build-wheels]
if: needs.check-changes.outputs.multimodal_gen == 'true' if: (always() && !failure() && !cancelled()) && needs.check-changes.outputs.multimodal_gen == 'true'
runs-on: 1-gpu-runner runs-on: 1-gpu-runner
steps: steps:
- name: Checkout code - name: Checkout code
@@ -343,7 +343,7 @@ jobs:
pytest -s -v --log-cli-level=INFO sglang/multimodal_gen/test/server/test_server_performance.py pytest -s -v --log-cli-level=INFO sglang/multimodal_gen/test/server/test_server_performance.py
unit-test-backend-1-gpu: unit-test-backend-1-gpu:
needs: [check-changes, stage-a-test-1, sgl-kernel-build-wheels] needs: [check-changes, stage-a-test-1]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 1-gpu-runner runs-on: 1-gpu-runner
@@ -377,7 +377,7 @@ jobs:
python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 15 python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 15
unit-test-backend-2-gpu: unit-test-backend-2-gpu:
needs: [check-changes, unit-test-backend-1-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-1-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 2-gpu-runner runs-on: 2-gpu-runner
@@ -410,7 +410,7 @@ jobs:
python3 run_suite.py --suite per-commit-2-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 python3 run_suite.py --suite per-commit-2-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
unit-test-backend-4-gpu: unit-test-backend-4-gpu:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 4-gpu-h100 runs-on: 4-gpu-h100
@@ -443,7 +443,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
unit-test-backend-8-gpu-h200: unit-test-backend-8-gpu-h200:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 8-gpu-h200 runs-on: 8-gpu-h200
@@ -476,7 +476,7 @@ jobs:
python3 run_suite.py --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 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: unit-test-backend-8-gpu-h20:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 8-gpu-h20 runs-on: 8-gpu-h20
@@ -510,7 +510,7 @@ jobs:
python3 run_suite.py --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 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: performance-test-1-gpu-part-1:
needs: [check-changes, sgl-kernel-build-wheels, stage-a-test-1] needs: [check-changes, stage-a-test-1]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 1-gpu-runner runs-on: 1-gpu-runner
@@ -571,7 +571,7 @@ jobs:
python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency_with_concurrent_adapter_updates python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency_with_concurrent_adapter_updates
performance-test-1-gpu-part-2: performance-test-1-gpu-part-2:
needs: [check-changes, sgl-kernel-build-wheels, stage-a-test-1] needs: [check-changes, stage-a-test-1]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 1-gpu-runner runs-on: 1-gpu-runner
@@ -624,7 +624,7 @@ jobs:
python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency
performance-test-1-gpu-part-3: performance-test-1-gpu-part-3:
needs: [check-changes, sgl-kernel-build-wheels, stage-a-test-1] needs: [check-changes, stage-a-test-1]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 1-gpu-runner runs-on: 1-gpu-runner
@@ -676,7 +676,7 @@ jobs:
rm -rf python/sglang/logs || true rm -rf python/sglang/logs || true
performance-test-2-gpu: performance-test-2-gpu:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 2-gpu-runner runs-on: 2-gpu-runner
@@ -735,7 +735,7 @@ jobs:
python3 -m unittest test_bench_serving.TestBenchServing.test_pp_long_context_prefill python3 -m unittest test_bench_serving.TestBenchServing.test_pp_long_context_prefill
accuracy-test-1-gpu: accuracy-test-1-gpu:
needs: [check-changes, sgl-kernel-build-wheels, stage-a-test-1] needs: [check-changes, stage-a-test-1]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 1-gpu-runner runs-on: 1-gpu-runner
@@ -767,7 +767,7 @@ jobs:
python3 test_eval_accuracy_large.py python3 test_eval_accuracy_large.py
accuracy-test-2-gpu: accuracy-test-2-gpu:
needs: [check-changes, accuracy-test-1-gpu, sgl-kernel-build-wheels] needs: [check-changes, accuracy-test-1-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 2-gpu-runner runs-on: 2-gpu-runner
@@ -799,7 +799,7 @@ jobs:
python3 test_moe_eval_accuracy_large.py python3 test_moe_eval_accuracy_large.py
unit-test-deepep-4-gpu: unit-test-deepep-4-gpu:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 4-gpu-h100 runs-on: 4-gpu-h100
@@ -828,7 +828,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu-deepep python3 run_suite.py --suite per-commit-4-gpu-deepep
unit-test-deepep-8-gpu: unit-test-deepep-8-gpu:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 8-gpu-h200 runs-on: 8-gpu-h200
@@ -857,7 +857,7 @@ jobs:
python3 run_suite.py --suite per-commit-8-gpu-h200-deepep python3 run_suite.py --suite per-commit-8-gpu-h200-deepep
unit-test-backend-4-gpu-b200: unit-test-backend-4-gpu-b200:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels] needs: [check-changes, unit-test-backend-2-gpu]
if: always() && !failure() && !cancelled() && if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 4-gpu-b200 runs-on: 4-gpu-b200