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

Cleanup uesless env (#5270)

Browse Source 
`VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP` is not used anywhere, let's
remove it.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-24 22:07:59 +08:00
committed by GitHub
parent 5018f2d8fd
commit fb3d6ca08c
3 changed files with 0 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm_ascend/envs.py
View File

@@ -68,11 +68,6 @@ env_variables: Dict[str, Callable[[], Any]] = {
# that the correct package is installed.
"VLLM_VERSION":
lambda: os.getenv("VLLM_VERSION", None),
# Whether to enable fused_experts_allgather_ep. MoeInitRoutingV3 and
# GroupedMatmulFinalizeRouting operators are combined to implement EP.
"VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP":
lambda: bool(int(os.getenv("VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP", '0'))
),
# Whether to enable the model execute time observe profile. Disable it when
# running vllm ascend in production environment.
"VLLM_ASCEND_MODEL_EXECUTE_TIME_OBSERVE":