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

[Attention] Use FA4 for MLA prefill (#34732)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-03-12 12:10:17 -04:00
committed by GitHub
parent 85199f9681
commit f444c05c32
9 changed files with 413 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
cmake/external_projects/vllm_flash_attn.cmake
View File

@@ -39,7 +39,7 @@ else()
FetchContent_Declare(
vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG 140c00c0241bb60cc6e44e7c1be9998d4b20d8d2
GIT_TAG 1488682bb545f7d020e958a33116b1419d1cfc83
GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn