minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[XPU][CI] disable SYCL_CACHE_PERSISTENT to fix topk segfault (#34567)

Browse Source 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
ashwini rathi
2026-08-13 11:19:39 +08:00
committed by GitHub
co-authored by Claude Opus 4.7
parent 5efe9b104d
commit d44c836cfd
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/ci/xpu/xpu_ci_start_container.sh
+4 -1
View File
@@ -128,6 +128,9 @@ echo "Launching container: ${CONTAINER_NAME} from ${IMAGE}"
# SGLANG_SERVER_LAUNCH_TIMEOUT=36000 matches /data/pgirijal/scripts/setup_upstream_env.sh: # SGLANG_SERVER_LAUNCH_TIMEOUT=36000 matches /data/pgirijal/scripts/setup_upstream_env.sh:
# 4-GPU MoE loads (Qwen3.5-35B-A3B, gemma-4-26B-A4B, ...) on Arc Pro B60 can # 4-GPU MoE loads (Qwen3.5-35B-A3B, gemma-4-26B-A4B, ...) on Arc Pro B60 can
# take >1h from a cold HF cache, so give sglang server startup a 10h ceiling. # take >1h from a cold HF cache, so give sglang server startup a 10h ceiling.
# SYCL_CACHE_PERSISTENT=0: the SYCL runtime's persistent kernel cache mishandles
# torch 2.13's XPU aten.topk kernel on compute-runtime 26.05 / IGC 2.28 -- reload
# segfaults inside libsycl. Keep off until Intel ships a fix in newer runtimes.
docker run -dt \ docker run -dt \
--shm-size 8g \ --shm-size 8g \
--group-add 992 \ --group-add 992 \
@@ -145,7 +148,7 @@ docker run -dt \
-e NEO_CACHE_DIR=/root/.cache/sglang-xpu/neo \ -e NEO_CACHE_DIR=/root/.cache/sglang-xpu/neo \
-e NEO_CACHE_PERSISTENT=1 \ -e NEO_CACHE_PERSISTENT=1 \
-e SYCL_CACHE_DIR=/root/.cache/sglang-xpu/sycl \ -e SYCL_CACHE_DIR=/root/.cache/sglang-xpu/sycl \
-e SYCL_CACHE_PERSISTENT=1 \ -e SYCL_CACHE_PERSISTENT=0 \
"${GPU_AFFINITY_ARGS[@]}" \ "${GPU_AFFINITY_ARGS[@]}" \
--name "${CONTAINER_NAME}" \ --name "${CONTAINER_NAME}" \
"${IMAGE}" "${IMAGE}"