chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 14 Packages Projects Releases Wiki Activity

[Refactore] [CI] Remove redundant CI test runs step 2 (#17584)

Browse Source
This commit is contained in:
Makcum888e
2026-01-24 23:39:48 -08:00
committed by GitHub
parent 9bd92ba0f6
commit d1042e0d62
36 changed files with 199 additions and 196 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd.yml
+44 -43
View File
@@ -92,7 +92,8 @@ jobs:
- "python/sglang/!(multimodal_gen)/**"
- "python/pyproject_rocm.toml"
- "python/pyproject_other.toml"
- "scripts/ci/**"
- "scripts/ci/amd/*"
- "scripts/ci/utils/*"
- "test/**"
- ".github/workflows/pr-test-amd.yml"
sgl_kernel:
@@ -131,13 +132,13 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd_ci_install_dependency.sh
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 14
@@ -179,13 +180,13 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd_ci_install_dependency.sh
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
@@ -222,18 +223,18 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd_ci_install_dependency.sh
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 10
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd
stage-b-test-small-1-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
@@ -263,17 +264,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800
stage-b-test-small-1-gpu-amd-mi35x:
needs: [check-changes, stage-a-test-1-amd]
@@ -302,17 +303,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x
stage-b-test-large-2-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
@@ -341,17 +342,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd
multimodal-gen-test-1-gpu-amd:
needs: [check-changes]
@@ -381,13 +382,13 @@ jobs:
pattern: wheel-python3.10-cuda12.9
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd_ci_install_dependency.sh diffusion
bash scripts/ci/amd/amd_ci_install_dependency.sh diffusion
- name: Setup kernel caches
run: |
@@ -501,13 +502,13 @@ jobs:
pattern: wheel-python3.10-cuda12.9
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd_ci_install_dependency.sh diffusion
bash scripts/ci/amd/amd_ci_install_dependency.sh diffusion
- name: Setup kernel caches
run: |
@@ -622,23 +623,23 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Test RCCL multi-GPU communication
timeout-minutes: 5
run: |
echo "Testing RCCL multi-GPU communication with debug info..."
docker exec ci_sglang bash -c "cd /sglang-checkout && NCCL_DEBUG=INFO RCCL_DEBUG=INFO torchrun --nproc_per_node=8 scripts/ci/test_rccl_multi_gpu.py"
docker exec ci_sglang bash -c "cd /sglang-checkout && NCCL_DEBUG=INFO RCCL_DEBUG=INFO torchrun --nproc_per_node=8 scripts/ci/amd/test_rccl_multi_gpu.py"
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
stage-c-test-large-8-gpu-amd-mi35x:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
@@ -668,17 +669,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
stage-b-test-small-1-gpu-performance-amd:
needs: [check-changes, call-gate, stage-a-test-1-amd]
@@ -707,17 +708,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-performance-amd --timeout-per-file 1200
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-performance-amd --timeout-per-file 1200
stage-b-test-large-1-gpu-performance-amd:
needs: [check-changes, call-gate, stage-a-test-1-amd]
@@ -747,17 +748,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-performance-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1200
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-performance-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1200
stage-b-test-large-2-gpu-performance-amd:
needs: [check-changes, call-gate, stage-a-test-1-amd]
@@ -786,17 +787,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-performance-amd --timeout-per-file 1200
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-performance-amd --timeout-per-file 1200
stage-b-test-small-1-gpu-accuracy-amd:
needs: [check-changes, stage-a-test-1-amd]
@@ -825,17 +826,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER=0 python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-accuracy-amd --timeout-per-file 1800
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER=0 python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-accuracy-amd --timeout-per-file 1800
stage-b-test-large-2-gpu-accuracy-amd:
needs: [check-changes, stage-a-test-1-amd]
@@ -864,17 +865,17 @@ jobs:
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-accuracy-amd --timeout-per-file 1800
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-accuracy-amd --timeout-per-file 1800
pr-test-amd-finish:
needs: