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
[Attention] FA3 Attention Sinks Perf Boost (#22478)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Lucas Wilkinson committed
Aug 15, 2025 at 17:41 UTC
177e55e3bd3dbb54089d9062b763a413c8718dff
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 93cf5a08f421a3efd0c4a7e005ef8f742b578ce0
41
+ GIT_TAG 2d3b7508f67ad976f781e2042ace676419dd78dd
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