Only upload CUDA coredumps on test failure (#22301)

.github/workflows/nightly-test-nvidia.yml

@@ -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:

.github/workflows/pr-test-multimodal-gen.yml

@@ -100,7 +100,7 @@ jobs:
             $CONTINUE_ON_ERROR_FLAG
 
       - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.part }}
 
@@ -155,7 +155,7 @@ jobs:
             $CONTINUE_ON_ERROR_FLAG
 
       - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.part }}
 
@@ -204,7 +204,7 @@ jobs:
             $CONTINUE_ON_ERROR_FLAG
 
       - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
+        if: failure()
 
   multimodal-gen-unit-test:
     if: |

.github/workflows/pr-test.yml

@@ -602,7 +602,7 @@ jobs:
           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()
+        if: failure()
 
   stage-a-test-cpu:
     needs: [check-changes, call-gate]
@@ -711,7 +711,7 @@ jobs:
           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()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.partition }}
 
@@ -767,7 +767,7 @@ jobs:
           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()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.partition }}
 
@@ -822,7 +822,7 @@ jobs:
           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()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.partition }}
 
@@ -880,7 +880,7 @@ jobs:
           python3 -m pytest -q python/sglang/jit_kernel/tests/test_flash_attention_4.py
 
       - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
+        if: failure()
 
   call-multimodal-gen-tests:
     needs: [check-changes, call-gate, sgl-kernel-build-wheels]
@@ -962,7 +962,7 @@ jobs:
           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
-        if: always()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.part }}
 
@@ -1030,7 +1030,7 @@ jobs:
           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
-        if: always()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.part }}
 
@@ -1086,7 +1086,7 @@ jobs:
           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
-        if: always()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.part }}
 
@@ -1148,7 +1148,7 @@ jobs:
           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()
+        if: failure()
 
   stage-c-test-deepep-8-gpu-h200:
     needs: [check-changes, call-gate, wait-for-stage-b]
@@ -1209,7 +1209,7 @@ jobs:
           python3 run_suite.py --hw cuda --suite stage-c-test-deepep-8-gpu-h200 $CONTINUE_ON_ERROR_FLAG
 
       - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
+        if: failure()
 
   stage-c-test-4-gpu-b200:
     needs: [check-changes, call-gate, wait-for-stage-b]
@@ -1262,7 +1262,7 @@ jobs:
           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
-        if: always()
+        if: failure()
         with:
           artifact-suffix: ${{ matrix.part }}
 
@@ -1316,7 +1316,7 @@ jobs:
   #         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
-  #       if: always()
+  #       if: failure()
 
   pr-test-finish:
     needs:

.github/workflows/rerun-test.yml

@@ -111,7 +111,7 @@ jobs:
           echo "All $total test(s) passed in ${total_elapsed}s"
 
       - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
+        if: failure()
 
   rerun-test-cpu:
     if: inputs.is_cpu == 'true'