xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-11 06:17:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

[tiny] Remove unsupported TRITON_MLA backend from batch invariance (#28832)

Browse Source 
Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Bram Wasti 2025-11-22 08:00:50 -05:00 committed by GitHub
parent 2d4978a57e
commit 5f7209a793
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

@ -805,11 +805,11 @@ def override_envs_for_invariance():
"FLASH_ATTN", # best supported backend
"FLASHINFER",
"FLASH_ATTN_MLA",
"TRITON_MLA",
# Not yet supported MLA backends
# "FLASHMLA",
# "FLEX_ATTENTION", # IMA issue even if we disable batch invariance
# "FLASHINFER_MLA", https://github.com/vllm-project/vllm/pull/28967
# "TRITON_MLA",
]
if curr_attn_backend not in supported_backends:
warning = (