xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-05 06:57:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Feature] Batch Invariant for R1 TP 8 on Blackwell (#27229)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-10-21 13:25:55 -04:00 committed by GitHub
parent aa1356ec53
commit 86ed77022d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/batch_invariant.py
View File

@ -756,10 +756,10 @@ def override_envs_for_invariance():
"FLEX_ATTENTION",
"FLASHINFER",
"FLASH_ATTN_MLA",
"FLASHINFER_MLA",
"TRITON_MLA",
# Not yet supported MLA backends
# "FLASHMLA",
# "FLASHINFER_MLA",
]
if curr_attn_backend not in supported_backends:
warning = (