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 3, 19:00 UTC
[Attention] Sync FA with upstream (#41052)
Matthew Bonanni committed
May 12, 2026 at 23:34 UTC
dcacdf9a8860a86401127d1c8f93ebf3cfbfd026
1 file changed
+1
-1
cmake/external_projects/vllm_flash_attn.cmake
+1
-1
@@ -39,7 +39,7 @@ else()
39
FetchContent_Declare(
40
vllm-flash-attn
41
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
42
- GIT_TAG f5bc33cfc02c744d24a2e9d50e6db656de40611c
42
+ GIT_TAG bce29425653ec0fbc579d329883030e832d15ada
43
GIT_PROGRESS TRUE
44
# Don't share the vllm-flash-attn build between build types
45
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn