EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Fix typo of VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE (#1112)

Browse Source 
### What this PR does / why we need it?
Fix typo of VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?

CI passed

Signed-off-by: linfeng-yuan <1102311262@qq.com>
This commit is contained in:
linfeng-yuan
2025-06-07 19:45:33 +08:00
committed by GitHub
parent 20dedba5d1
commit b80a484864
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/patch/worker/patch_common/patch_sampler.py
View File

@@ -97,5 +97,5 @@ def topk_topp_forward_native(
Sampler.apply_min_p = apply_min_p
if envs.VLLM_ASCEND_ENABLE_TOPK_OPTIMZE:
if envs.VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE:
TopKTopPSampler.forward_native = topk_topp_forward_native