@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 68f11149d8
Fork 0

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