icer/qwen36_01
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix large completion probe timeout

Browse Source
This commit is contained in:
the magician
2026-07-15 22:20:25 +08:00
parent 163da44dfd
commit a7a2c722af
5 changed files with 149 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
qwen3_6_scripts/patch_ops.sh
View File

@@ -167,6 +167,8 @@ check "LOOP1_NATIVE" "$VLLM_PKG/model_executor/models/qwen3_5.py" "LOOP1_NAT
check "RMSNORM_NATIVE" "$VLLM_PKG/model_executor/models/qwen3_5.py" "RMSNORM_NATIVE"
check "PREFIX_FLASH" "$VLLM_PKG/attention/ops/paged_attn.py" "PREFIX_FLASH (paged_attn.py)"
check "_forward_prefix_flash" "$VLLM_PKG/attention/ops/paged_attn.py" "_forward_prefix_flash"
check "VLLM_BASIC_FASTPATH" "$VLLM_PKG/entrypoints/openai/api_server.py" "basic fastpath env gate"
check "_large_completion_output_fastpath" "$VLLM_PKG/entrypoints/openai/api_server.py" "completion large-output fastpath"
# libcusolver link present (else LOOP1_NATIVE silently falls back at runtime)
if [ -e /opt/sw_home/local/cuda/lib64/libcusolver.so ]; then