Migrate 4-GPU/8-GPU workflow jobs to stage-c and add CI registry decorators (#17299)

This commit is contained in:
Alison Shao
2026-01-31 22:37:22 -08:00
committed by GitHub
parent 95180484e9
commit a0bae4c343
39 changed files with 189 additions and 284 deletions

View File

@@ -1298,12 +1298,12 @@ jobs:
--total-partitions 2 \
$CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu:
stage-c-test-4-gpu-h100:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-4-gpu') ||
(inputs.target_stage == 'stage-c-test-4-gpu-h100') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1340,23 +1340,19 @@ jobs:
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-h100 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $CONTINUE_ON_ERROR_FLAG
unit-test-backend-8-gpu-h200:
stage-c-test-8-gpu-h200:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-8-gpu-h200') ||
(inputs.target_stage == 'stage-c-test-8-gpu-h200') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1399,23 +1395,19 @@ jobs:
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 4 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
unit-test-backend-8-gpu-h20:
stage-c-test-8-gpu-h20:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-8-gpu-h20') ||
(inputs.target_stage == 'stage-c-test-8-gpu-h20') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1453,23 +1445,19 @@ jobs:
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $CONTINUE_ON_ERROR_FLAG
unit-test-deepep-4-gpu:
stage-c-test-deepep-4-gpu:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-deepep-4-gpu') ||
(inputs.target_stage == 'stage-c-test-deepep-4-gpu') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1502,23 +1490,19 @@ jobs:
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-4-gpu-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-4-gpu $CONTINUE_ON_ERROR_FLAG
unit-test-deepep-8-gpu:
stage-c-test-deepep-8-gpu-h200:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-deepep-8-gpu') ||
(inputs.target_stage == 'stage-c-test-deepep-8-gpu-h200') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1551,23 +1535,19 @@ jobs:
- name: Run test
timeout-minutes: 45
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-8-gpu-h200-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-8-gpu-h200 $CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu-b200:
stage-c-test-4-gpu-b200:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-4-gpu-b200') ||
(inputs.target_stage == 'stage-c-test-4-gpu-b200') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1605,23 +1585,19 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu-gb200:
stage-c-test-4-gpu-gb200:
needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels-arm]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
(inputs.target_stage == 'stage-c-test-4-gpu-gb200') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1656,16 +1632,12 @@ jobs:
- name: Run test
timeout-minutes: 45
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
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 --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-gb200 --timeout-per-file 3600 $CONTINUE_ON_ERROR_FLAG
pr-test-finish:
needs:
@@ -1694,13 +1666,13 @@ jobs:
stage-b-test-large-2-gpu,
stage-c-test-large-4-gpu,
stage-b-test-4-gpu-b200,
unit-test-backend-4-gpu,
unit-test-backend-8-gpu-h20,
unit-test-backend-8-gpu-h200,
unit-test-deepep-4-gpu,
unit-test-deepep-8-gpu,
unit-test-backend-4-gpu-b200,
unit-test-backend-4-gpu-gb200,
stage-c-test-4-gpu-h100,
stage-c-test-8-gpu-h20,
stage-c-test-8-gpu-h200,
stage-c-test-deepep-4-gpu,
stage-c-test-deepep-8-gpu-h200,
stage-c-test-4-gpu-b200,
stage-c-test-4-gpu-gb200,
]
if: always()
runs-on: ubuntu-latest