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, 04:45 UTC
cmake: Update vllm_flash_attn for vllm_kernels (#20032)
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Eli Uriegas committed
Jun 24, 2025 at 15:44 UTC
0d06b533a0fcca7a62603c868df68235659d6935
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 2c6bcfc0feb3d9d4a57b243fc159a68aa9933f5b
41
+ GIT_TAG 5f3644181c7a15345ce20bfc65af117d3601b524
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