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 12, 18:30 UTC
[BugFix] Fix missing symbol triggering FA2 fallback on Hopper (#29107)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Lucas Wilkinson committed
Nov 21, 2025 at 16:58 UTC
c68c7b403dce632dbbbb6d2482ea86fe7bf53d51
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 71bb26f6295449be880344b93b51791cc009237d
41
+ GIT_TAG 86f8f157cf82aa2342743752b97788922dd7de43
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