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][Kernel] Fix perf regression caused by PR #12405 (#12434)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Lucas Wilkinson committed
Jan 26, 2025 at 14:09 UTC
68f11149d845a164c9bbf122ab3bee8c94290169
1 file changed
+1
-1
CMakeLists.txt
+1
-1
@@ -576,7 +576,7 @@ else()
576
FetchContent_Declare(
577
vllm-flash-attn
578
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
579
- GIT_TAG 9732b0ce005d1e6216864788502d5570004678f5
579
+ GIT_TAG d4e09037abf588af1ec47d0e966b237ee376876c
580
GIT_PROGRESS TRUE
581
# Don't share the vllm-flash-attn build between build types
582
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn