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 16, 00:45 UTC
[Bugfix] FA2 illegal memory access (#12848)
Lucas Wilkinson committed
Feb 6, 2025 at 22:54 UTC
ef533d25fba4b5ef8b4da9369de718c0773b9bce
1 file changed
+1
-1
CMakeLists.txt
+1
-1
@@ -581,7 +581,7 @@ else()
581
FetchContent_Declare(
582
vllm-flash-attn
583
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
584
- GIT_TAG d4e09037abf588af1ec47d0e966b237ee376876c
584
+ GIT_TAG 720c94869cf2e0ff5a706e9c7f1dce0939686ade
585
GIT_PROGRESS TRUE
586
# Don't share the vllm-flash-attn build between build types
587
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn