chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

ci: run Stage A CUDA tests as stage-a-test-small-1-gpu on 5090 (#20988)

Browse Source
This commit is contained in:
Lianmin Zheng
2026-03-20 02:55:16 -07:00
committed by GitHub
parent fa89d152c0
commit c1da420799
12 changed files with 78 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.github/workflows/pr-test-amd-rocm720.yml vendored
View File

@@ -35,7 +35,7 @@ on:
- ''
- sgl-kernel-unit-test-amd
- sgl-kernel-unit-test-2-gpu-amd
- stage-a-test-1-amd
- stage-a-test-small-1-gpu-amd
- jit-kernel-unit-test-amd
- stage-b-test-small-1-gpu-amd
- stage-b-test-small-1-gpu-amd-nondeterministic
@@ -246,12 +246,12 @@ jobs:
# =============================================== primary ====================================================
stage-a-test-1-amd:
stage-a-test-small-1-gpu-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-1-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-small-1-gpu-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -283,7 +283,7 @@ jobs:
- name: Run test
timeout-minutes: 10
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-small-1-gpu-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
jit-kernel-unit-test-amd:
needs: [check-changes]
@@ -984,7 +984,7 @@ jobs:
multimodal-gen-test-1-gpu-amd,
multimodal-gen-test-2-gpu-amd,
stage-a-test-1-amd,
stage-a-test-small-1-gpu-amd,
jit-kernel-unit-test-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-nondeterministic,

22
.github/workflows/pr-test-amd.yml vendored
View File

@@ -33,7 +33,7 @@ on:
- ''
- sgl-kernel-unit-test-amd
- sgl-kernel-unit-test-2-gpu-amd
- stage-a-test-1-amd
- stage-a-test-small-1-gpu-amd
- jit-kernel-unit-test-amd
- stage-b-test-small-1-gpu-amd
- stage-b-test-small-1-gpu-amd-nondeterministic
@@ -246,12 +246,12 @@ jobs:
# =============================================== primary ====================================================
stage-a-test-1-amd:
stage-a-test-small-1-gpu-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-1-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-small-1-gpu-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -284,7 +284,7 @@ jobs:
- name: Run test
timeout-minutes: 10
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-small-1-gpu-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
jit-kernel-unit-test-amd:
needs: [check-changes]
@@ -326,7 +326,7 @@ jobs:
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout" python3 -m pytest -q python/sglang/jit_kernel/tests/test_store_cache.py
stage-b-test-small-1-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
needs: [check-changes, stage-a-test-small-1-gpu-amd]
if: |
always() &&
(
@@ -366,7 +366,7 @@ jobs:
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 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-nondeterministic:
needs: [check-changes, stage-a-test-1-amd]
needs: [check-changes, stage-a-test-small-1-gpu-amd]
if: |
always() &&
(
@@ -405,7 +405,7 @@ jobs:
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-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-mi35x:
needs: [check-changes, stage-a-test-1-amd]
needs: [check-changes, stage-a-test-small-1-gpu-amd]
if: |
always() &&
(
@@ -444,7 +444,7 @@ jobs:
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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-1-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
needs: [check-changes, stage-a-test-small-1-gpu-amd]
if: |
always() &&
(
@@ -484,7 +484,7 @@ jobs:
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-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-2-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
needs: [check-changes, stage-a-test-small-1-gpu-amd]
if: |
always() &&
(
@@ -868,7 +868,7 @@ jobs:
# =============================================== Disaggregation ====================================================
stage-b-test-large-8-gpu-35x-disaggregation-amd:
needs: [check-changes, stage-a-test-1-amd]
needs: [check-changes, stage-a-test-small-1-gpu-amd]
if: |
always() &&
(
@@ -989,7 +989,7 @@ jobs:
multimodal-gen-test-1-gpu-amd,
multimodal-gen-test-2-gpu-amd,
stage-a-test-1-amd,
stage-a-test-small-1-gpu-amd,
jit-kernel-unit-test-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-nondeterministic,

103
.github/workflows/pr-test.yml vendored
View File

@@ -333,7 +333,7 @@ jobs:
id: wait
with:
stage-name: stage-a
jobs: '["stage-a-test-1", "stage-a-cpu-only"]'
jobs: '["stage-a-test-small-1-gpu", "stage-a-cpu-only"]'
max-wait-minutes: '240'
wait-for-stage-b:
@@ -783,20 +783,23 @@ jobs:
# =============================================== primary ====================================================
stage-a-test-1:
# Runs on 5090 (32GB, SM120)
stage-a-test-small-1-gpu:
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-a-test-1') ||
(inputs.target_stage == 'stage-a-test-small-1-gpu') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: 1-gpu-runner
runs-on: 1-gpu-5090
timeout-minutes: 240
env:
IS_BLACKWELL: "1"
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -818,13 +821,11 @@ jobs:
- name: Run test
timeout-minutes: 10
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-a-test-1 $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-a-test-small-1-gpu $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
@@ -866,12 +867,10 @@ jobs:
- name: Run test
timeout-minutes: 10
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cpu --suite stage-a-cpu-only $CONTINUE_ON_ERROR_FLAG
# Runs on 5090 (32GB, SM120)
@@ -921,13 +920,11 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
source /etc/profile.d/sglang-ci.sh
cd test/
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 8 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -976,12 +973,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-b-test-large-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 14 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1031,12 +1026,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1082,12 +1075,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-b-test-4-gpu-b200 $CONTINUE_ON_ERROR_FLAG
- name: Run FA4 jit_kernel tests (SM100+)
@@ -1138,12 +1129,9 @@ jobs:
timeout-minutes: 240
env:
RUNAI_STREAMER_MEMORY_LIMIT: 0
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd python
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 sglang/multimodal_gen/test/run_suite.py \
--suite 1-gpu \
--partition-id ${{ matrix.part }} \
@@ -1196,12 +1184,9 @@ jobs:
timeout-minutes: 240
env:
RUNAI_STREAMER_MEMORY_LIMIT: 0
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd python
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 sglang/multimodal_gen/test/run_suite.py \
--suite 2-gpu \
--partition-id ${{ matrix.part }} \
@@ -1291,12 +1276,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-h100 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1357,12 +1340,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-c-test-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1411,12 +1392,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-c-test-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1471,12 +1450,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-4-gpu $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1530,12 +1507,10 @@ jobs:
- name: Run test
timeout-minutes: 45
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-8-gpu-h200 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1581,12 +1556,10 @@ jobs:
- name: Run test
timeout-minutes: 30
env:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 4 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
@@ -1633,12 +1606,10 @@ jobs:
#
# - name: Run test
# timeout-minutes: 45
# env:
# CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
# run: |
# cd test
# CONTINUE_ON_ERROR_FLAG=""
# if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
# CONTINUE_ON_ERROR_FLAG="--continue-on-error"
# fi
# python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-gb200 --timeout-per-file 3600 $CONTINUE_ON_ERROR_FLAG
#
# - uses: ./.github/actions/upload-cuda-coredumps
@@ -1667,7 +1638,7 @@ jobs:
multimodal-gen-test-1-gpu,
multimodal-gen-test-2-gpu,
stage-a-test-1,
stage-a-test-small-1-gpu,
stage-a-cpu-only,
stage-b-test-small-1-gpu,
stage-b-test-large-1-gpu,