biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
This commit is contained in:
Andreas Karatzas
2025-11-11 20:34:36 -06:00
committed by GitHub
parent 7f829be7d3
commit 9f0247cfa4
15 changed files with 12 additions and 1588 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/usage/usage_lib.py
View File

@@ -37,7 +37,6 @@ _GLOBAL_RUNTIME_DATA = dict[str, str | int | bool]()
_USAGE_ENV_VARS_TO_COLLECT = [
"VLLM_USE_MODELSCOPE",
"VLLM_USE_TRITON_FLASH_ATTN",
"VLLM_ATTENTION_BACKEND",
"VLLM_USE_FLASHINFER_SAMPLER",
"VLLM_PP_LAYER_PARTITION",