A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Bugfix] Update FA commit hash (#22546)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Thomas Parnell committed
Aug 9, 2025 at 01:10 UTC
bd875d2eb71b130cbc2b68bf0e2dd285f5c7348d
1 file changed
+1
-1
cmake/external_projects/vllm_flash_attn.cmake
+1
-1
@@ -38,7 +38,7 @@ else()
38
FetchContent_Declare(
39
vllm-flash-attn
40
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
41
- GIT_TAG 6dbc6e011a3ebe9349eeb74578940dd7095436ba
41
+ GIT_TAG 93cf5a08f421a3efd0c4a7e005ef8f742b578ce0
42
GIT_PROGRESS TRUE
43
# Don't share the vllm-flash-attn build between build types
44
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn