Skip to content

GitLab

Unverified Commit e3c876dc authored by Woosuk Kwon's avatar Woosuk Kwon Committed by GitHub
Browse files

Upgrade FA3 for attention sink (#22313) 


Signed-off-by: default avatarWoosuk Kwon <woosuk.kwon@berkeley.edu>
parent 5d5d419c
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
cmake/external_projects/vllm_flash_attn.cmake
View file @ e3c876dc
......@@ -38,7 +38,7 @@ else()
FetchContent_Declare(
vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG 1c2624e53c078854e0637ee566c72fe2107e75f4
GIT_TAG b99f8c821771fd11feb66d5c89661e9858fde359
GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment