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
[BugFix] Fix FA2 RuntimeError when sinks is provided (#22365)
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
Lucas Wilkinson committed
Aug 6, 2025 at 11:03 UTC
2cb6ef8996320273705933d5b24fc6674eb95de8
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 b99f8c821771fd11feb66d5c89661e9858fde359
41
+ GIT_TAG 6dbc6e011a3ebe9349eeb74578940dd7095436ba
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