Only upload CUDA coredumps on test failure (#22301)

This commit is contained in:
Liangsheng Yin
2026-04-07 18:07:28 -07:00
committed by GitHub
parent dd73e9a62e
commit 8c3d80eabe
4 changed files with 32 additions and 32 deletions
+16 -16
View File
@@ -76,7 +76,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-1-gpu --nightly --continue-on-error
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# JIT kernel full unit tests (expanded parameter ranges via SGLANG_JIT_KERNEL_RUN_FULL_TESTS)
nightly-test-kernel-1-gpu-h100:
@@ -110,7 +110,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-kernel-1-gpu --nightly --continue-on-error
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
nightly-test-kernel-8-gpu-h200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-8-gpu-h200')
@@ -140,7 +140,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-kernel-8-gpu-h200 --nightly --continue-on-error
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# General tests - 4 GPU H100
nightly-test-general-4-gpu-h100:
@@ -165,7 +165,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-4-gpu --nightly --continue-on-error
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# General tests - 8 GPU H200
nightly-test-general-8-gpu-h200:
@@ -249,7 +249,7 @@ jobs:
if-no-files-found: ignore
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
with:
artifact-suffix: ${{ matrix.partition }}
@@ -280,7 +280,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-8-gpu-h20 --nightly --continue-on-error
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# General tests - 8 GPU B200
nightly-test-general-8-gpu-b200:
@@ -353,7 +353,7 @@ jobs:
if-no-files-found: ignore
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
with:
artifact-suffix: ${{ matrix.partition }}
@@ -380,7 +380,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-eval-text-2-gpu --nightly --continue-on-error --timeout-per-file 4500
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# Text model performance tests
nightly-test-text-perf-2-gpu-h100:
@@ -418,7 +418,7 @@ jobs:
python3 scripts/ci/utils/publish_traces.py --traces-dir test/performance_profiles_text_models
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# VLM accuracy tests
nightly-test-vlm-accuracy-2-gpu-h100:
@@ -443,7 +443,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-eval-vlm-2-gpu --nightly --continue-on-error --timeout-per-file 9000
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# VLM performance tests
nightly-test-vlm-perf-2-gpu-h100:
@@ -481,7 +481,7 @@ jobs:
python3 scripts/ci/utils/publish_traces.py --traces-dir test/performance_profiles_vlms
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# diffusion performance tests
nightly-test-multimodal-server-1-gpu:
@@ -538,7 +538,7 @@ jobs:
if-no-files-found: ignore
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
with:
artifact-suffix: ${{ matrix.part }}
@@ -596,7 +596,7 @@ jobs:
if-no-files-found: ignore
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
with:
artifact-suffix: ${{ matrix.part }}
@@ -623,7 +623,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-4-gpu-b200 --nightly --continue-on-error --timeout-per-file 12000
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# Specialized B200 tests - 8 GPU, for specific backends and configs
nightly-test-specialized-8-gpu-b200:
@@ -652,7 +652,7 @@ jobs:
python3 run_suite.py --hw cuda --suite nightly-8-gpu-b200 --nightly --continue-on-error --timeout-per-file 2400
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# Diffusion cross-framework comparison
nightly-test-diffusion-comparison:
@@ -716,7 +716,7 @@ jobs:
if-no-files-found: ignore
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
if: failure()
# Consolidate performance metrics from all jobs
consolidate-metrics: