Skip to content

Commit

Permalink
[Kernel] Update vllm-flash-attn version to reduce CPU overheads (#10742)
Browse files Browse the repository at this point in the history
Signed-off-by: Woosuk Kwon <[email protected]>
  • Loading branch information
WoosukKwon authored Nov 28, 2024
1 parent 5fc5ce0 commit 8c1e77f
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -522,7 +522,7 @@ else()
FetchContent_Declare(
vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG d886f88165702b3c7e7744502772cd98b06be9e1
GIT_TAG fdf6d72b48aea41f4ae6a89139a453dae554abc8
GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn
Expand Down

0 comments on commit 8c1e77f

Please sign in to comment.