[AMD] Clear pre-built AITER kernels and warmup to prevent segfaults and test timeouts (#15318)

This commit is contained in:
sunxxuns
2025-12-18 14:00:09 -08:00
committed by GitHub
parent e0026f7c92
commit e0963a6cb1
4 changed files with 142 additions and 3 deletions
+10
View File
@@ -79,3 +79,13 @@ docker cp ./dummy-grok ci_sglang:/
docker exec ci_sglang pip install --cache-dir=/sgl-data/pip-cache huggingface_hub[hf_xet]
docker exec ci_sglang pip install --cache-dir=/sgl-data/pip-cache pytest
# Clear pre-built AITER kernels from Docker image to avoid segfaults
# The Docker image may contain pre-compiled kernels incompatible with the current environment
echo "Clearing pre-built AITER kernels from Docker image..."
docker exec ci_sglang find /sgl-workspace/aiter/aiter/jit -name "*.so" -delete 2>/dev/null || true
docker exec ci_sglang ls -la /sgl-workspace/aiter/aiter/jit/ 2>/dev/null || echo "jit dir empty or not found"
# Pre-build AITER kernels to avoid timeout during tests
echo "Warming up AITER JIT kernels..."
docker exec -e SGLANG_USE_AITER=1 ci_sglang python3 /sglang-checkout/scripts/ci/amd_ci_warmup_aiter.py || echo "AITER warmup completed (some kernels may not be available)"