[ci] Move dpsk-r1-fp4 b200 test to stage b (#15084)

This commit is contained in:
Qiaolin Yu
2025-12-13 23:14:08 -08:00
committed by GitHub
parent 2ae5bed193
commit 729529190d
5 changed files with 58 additions and 9 deletions

View File

@@ -609,6 +609,48 @@ jobs:
cd test/srt
python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 15
stage-b-test-4-gpu-b200:
needs: [check-changes, call-gate, unit-test-backend-1-gpu]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-4-gpu-b200') ||
(
!inputs.target_stage &&
(github.event_name == 'schedule' || (!failure() && !cancelled())) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: ${{ needs.check-changes.outputs.b200_runner }}
env:
RUNNER_LABELS: ${{ needs.check-changes.outputs.b200_runner }}
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v6
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
cd test/srt
IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200-stage-b --timeout-per-file 1800
unit-test-backend-2-gpu:
needs: [check-changes, call-gate, unit-test-backend-1-gpu]
if: |
@@ -651,7 +693,7 @@ 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, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -692,7 +734,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 3
unit-test-backend-8-gpu-h200:
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -739,7 +781,7 @@ 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, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -966,7 +1008,7 @@ jobs:
python3 -m unittest test_bench_serving.TestBenchServing.test_embeddings_api_batch_scaling
performance-test-2-gpu:
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -1113,7 +1155,7 @@ jobs:
python3 test_moe_eval_accuracy_large.py
unit-test-deepep-4-gpu:
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -1150,7 +1192,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu-deepep
unit-test-deepep-8-gpu:
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -1187,7 +1229,7 @@ jobs:
python3 run_suite.py --suite per-commit-8-gpu-h200-deepep
unit-test-backend-4-gpu-b200:
needs: [check-changes, call-gate, unit-test-backend-2-gpu]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
if: |
always() &&
(
@@ -1229,7 +1271,7 @@ jobs:
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
unit-test-backend-4-gpu-gb200:
needs: [check-changes, call-gate, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200, sgl-kernel-build-wheels-arm]
if: |
always() &&
(
@@ -1287,6 +1329,7 @@ jobs:
quantization-test,
unit-test-backend-1-gpu,
unit-test-backend-2-gpu,
stage-b-test-4-gpu-b200,
unit-test-backend-4-gpu,
unit-test-backend-8-gpu-h20,
unit-test-backend-8-gpu-h200,