xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 12:24:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Attention] FA3 decode perf improvement - single mma warp group support for head dim 128 (#16864)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson 2025-04-24 23:12:21 -04:00 committed by GitHub
parent eef364723c
commit 41ca7eb491
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
cmake/external_projects/vllm_flash_attn.cmake
View File

@ -38,7 +38,7 @@ else()
FetchContent_Declare( FetchContent_Declare(
vllm-flash-attn vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG 0a721daebe4fa7149f06ecf3d3eabeb6dcd0f1fa GIT_TAG e93779c59ba4905e56e5c39dc2c1904ada71fa21
GIT_PROGRESS TRUE GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types # Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn