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 15, 06:00 UTC
[Wheel Size] Only build FA2 8.0+PTX (#19336)
Lucas Wilkinson committed
Jun 16, 2025 at 23:32 UTC
07334959d81076d49ea78b9ab3bfcafa4227f0ee
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 8798f27777fb57f447070301bf33a9f9c607f491
41
+ GIT_TAG 763ad155a1c826f71ff318f41edb1e4e5e376ddb
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