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

[Bugfix] quick fix balance scheduling patch (#5281)

Browse Source 
### What this PR does / why we need it?
quick fix balance scheduling patch

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: GDzhu01 <809721801@qq.com>
This commit is contained in:
Zhu Yi Lin
2025-12-23 21:23:05 +08:00
committed by GitHub
parent ffe51eedd6
commit e14514e2fd
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/envs.py
View File

@@ -146,7 +146,7 @@ env_variables: Dict[str, Callable[[], Any]] = {
lambda: int(os.getenv("VLLM_ASCEND_ENABLE_FUSED_MC2", '0')), lambda: int(os.getenv("VLLM_ASCEND_ENABLE_FUSED_MC2", '0')),
# Whether to anbale balance scheduling # Whether to anbale balance scheduling
"VLLM_ASCEND_BALANCE_SCHEDULING": "VLLM_ASCEND_BALANCE_SCHEDULING":
lambda: bool(os.getenv("VLLM_ASCEND_BALANCE_SCHEDULING", '0')), lambda: bool(int(os.getenv("VLLM_ASCEND_BALANCE_SCHEDULING", '0'))),
} }
# end-env-vars-definition # end-env-vars-definition