ci: unify PR test suite naming (#21187)
This commit is contained in:
@@ -345,7 +345,7 @@ jobs:
|
||||
id: wait
|
||||
with:
|
||||
stage-name: stage-a
|
||||
jobs: '["stage-a-test-small-1-gpu", "stage-a-cpu-only"]'
|
||||
jobs: '["stage-a-test-1-gpu-small", "stage-a-test-cpu"]'
|
||||
max-wait-minutes: '240'
|
||||
|
||||
wait-for-stage-b:
|
||||
@@ -377,9 +377,9 @@ jobs:
|
||||
stage-name: stage-b
|
||||
jobs: |
|
||||
[
|
||||
{"prefix": "stage-b-test-small-1-gpu", "expected_count": 8},
|
||||
{"prefix": "stage-b-test-large-1-gpu", "expected_count": 14},
|
||||
{"prefix": "stage-b-test-large-2-gpu", "expected_count": 4},
|
||||
{"prefix": "stage-b-test-1-gpu-small", "expected_count": 8},
|
||||
{"prefix": "stage-b-test-1-gpu-large", "expected_count": 14},
|
||||
{"prefix": "stage-b-test-2-gpu-large", "expected_count": 4},
|
||||
{"prefix": "stage-b-test-4-gpu-b200", "expected_count": 1}
|
||||
]
|
||||
max-wait-minutes: '480'
|
||||
@@ -833,12 +833,12 @@ jobs:
|
||||
# =============================================== primary ====================================================
|
||||
|
||||
# Runs on 5090 (32GB, SM120)
|
||||
stage-a-test-small-1-gpu:
|
||||
stage-a-test-1-gpu-small:
|
||||
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'stage-a-test-small-1-gpu') ||
|
||||
(inputs.target_stage == 'stage-a-test-1-gpu-small') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
|
||||
@@ -876,17 +876,17 @@ jobs:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
cd test/
|
||||
python3 run_suite.py --hw cuda --suite stage-a-test-small-1-gpu $CONTINUE_ON_ERROR_FLAG
|
||||
python3 run_suite.py --hw cuda --suite stage-a-test-1-gpu-small $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: always()
|
||||
|
||||
stage-a-cpu-only:
|
||||
stage-a-test-cpu:
|
||||
needs: [check-changes, call-gate]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'stage-a-cpu-only') ||
|
||||
(inputs.target_stage == 'stage-a-test-cpu') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
|
||||
@@ -932,15 +932,15 @@ jobs:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
cd test/
|
||||
python3 run_suite.py --hw cpu --suite stage-a-cpu-only $CONTINUE_ON_ERROR_FLAG
|
||||
python3 run_suite.py --hw cpu --suite stage-a-test-cpu $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
# Runs on 5090 (32GB, SM120)
|
||||
stage-b-test-small-1-gpu:
|
||||
stage-b-test-1-gpu-small:
|
||||
needs: [check-changes, call-gate, wait-for-stage-a, sgl-kernel-build-wheels]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'stage-b-test-small-1-gpu') ||
|
||||
(inputs.target_stage == 'stage-b-test-1-gpu-small') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
|
||||
@@ -988,7 +988,7 @@ jobs:
|
||||
run: |
|
||||
source /etc/profile.d/sglang-ci.sh
|
||||
cd test/
|
||||
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
|
||||
python3 run_suite.py --hw cuda --suite stage-b-test-1-gpu-small --auto-partition-id ${{ matrix.partition }} --auto-partition-size 8 $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: always()
|
||||
@@ -996,12 +996,12 @@ jobs:
|
||||
artifact-suffix: ${{ matrix.partition }}
|
||||
|
||||
# Runs on H100 (80GB, SM90) - tests that don't pass on 5090 (FA3, FP8, high VRAM, etc.)
|
||||
stage-b-test-large-1-gpu:
|
||||
stage-b-test-1-gpu-large:
|
||||
needs: [check-changes, call-gate, wait-for-stage-a, sgl-kernel-build-wheels]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'stage-b-test-large-1-gpu') ||
|
||||
(inputs.target_stage == 'stage-b-test-1-gpu-large') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
|
||||
@@ -1044,19 +1044,19 @@ jobs:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
cd test/
|
||||
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
|
||||
python3 run_suite.py --hw cuda --suite stage-b-test-1-gpu-large --auto-partition-id ${{ matrix.partition }} --auto-partition-size 14 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: always()
|
||||
with:
|
||||
artifact-suffix: ${{ matrix.partition }}
|
||||
|
||||
stage-b-test-large-2-gpu:
|
||||
stage-b-test-2-gpu-large:
|
||||
needs: [check-changes, call-gate, wait-for-stage-a, sgl-kernel-build-wheels]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'stage-b-test-large-2-gpu') ||
|
||||
(inputs.target_stage == 'stage-b-test-2-gpu-large') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
|
||||
@@ -1101,7 +1101,7 @@ jobs:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
cd test/
|
||||
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
|
||||
python3 run_suite.py --hw cuda --suite stage-b-test-2-gpu-large --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: always()
|
||||
@@ -1502,12 +1502,12 @@ jobs:
|
||||
with:
|
||||
artifact-suffix: ${{ matrix.part }}
|
||||
|
||||
stage-c-test-deepep-4-gpu:
|
||||
stage-c-test-deepep-4-gpu-h100:
|
||||
needs: [check-changes, call-gate, wait-for-stage-b]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'stage-c-test-deepep-4-gpu') ||
|
||||
(inputs.target_stage == 'stage-c-test-deepep-4-gpu-h100') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
|
||||
@@ -1557,7 +1557,7 @@ jobs:
|
||||
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||
run: |
|
||||
cd test
|
||||
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-4-gpu $CONTINUE_ON_ERROR_FLAG
|
||||
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-4-gpu-h100 $CONTINUE_ON_ERROR_FLAG
|
||||
|
||||
- uses: ./.github/actions/upload-cuda-coredumps
|
||||
if: always()
|
||||
@@ -1753,16 +1753,16 @@ jobs:
|
||||
multimodal-gen-test-1-gpu,
|
||||
multimodal-gen-test-2-gpu,
|
||||
|
||||
stage-a-test-small-1-gpu,
|
||||
stage-a-cpu-only,
|
||||
stage-b-test-small-1-gpu,
|
||||
stage-b-test-large-1-gpu,
|
||||
stage-b-test-large-2-gpu,
|
||||
stage-a-test-1-gpu-small,
|
||||
stage-a-test-cpu,
|
||||
stage-b-test-1-gpu-small,
|
||||
stage-b-test-1-gpu-large,
|
||||
stage-b-test-2-gpu-large,
|
||||
stage-b-test-4-gpu-b200,
|
||||
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-4-gpu-h100,
|
||||
stage-c-test-deepep-8-gpu-h200,
|
||||
stage-c-test-4-gpu-b200,
|
||||
# stage-c-test-4-gpu-gb200, # Temporarily disabled — no GB200 runner
|
||||
|
||||
Reference in New Issue
Block a user