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
[MLA] Bump FlashMLA (#27354)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Matthew Bonanni committed
Oct 22, 2025 at 18:48 UTC
b4fda58a2d0e458e0186e4caa4354b3d07153c70
1 file changed
+1
-1
cmake/external_projects/flashmla.cmake
+1
-1
@@ -19,7 +19,7 @@ else()
19
FetchContent_Declare(
20
flashmla
21
GIT_REPOSITORY https://github.com/vllm-project/FlashMLA
22
- GIT_TAG 28417e516fcbf6257a422ba117ef5b6f44da5682
22
+ GIT_TAG 46d64a8ebef03fa50b4ae74937276a5c940e3f95
23
GIT_PROGRESS TRUE
24
CONFIGURE_COMMAND ""
25
BUILD_COMMAND ""