Fix potential memory fault issue and ncclSystemError in CI test (#8681)

Co-authored-by: wunhuang <wunhuang@amd.com>
2025-08-05 12:19:37 -07:00
parent 4f4e0e4162
commit 32d9e39a29
3 changed files with 7 additions and 9 deletions
@@ -124,6 +124,7 @@ echo "Starting container: ci_sglang"
 docker run -dt --user root --device=/dev/kfd $DEVICE_FLAG \
  -v "${GITHUB_WORKSPACE:-$PWD}:/sglang-checkout" \
  --ipc=host --group-add video \
+  --shm-size 32g \
  --cap-add=SYS_PTRACE \
  -e HF_TOKEN="${HF_TOKEN:-}" \
  --security-opt seccomp=unconfined \