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
[Perf] Improve/Fix-regression for FA3 in High QPS regimes (#19463)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Lucas Wilkinson committed
Jun 24, 2025 at 13:09 UTC
a045b7e89a2424ec3b152ee57be2931eedb2abd2
2 files changed
+2
-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 763ad155a1c826f71ff318f41edb1e4e5e376ddb
41
+ GIT_TAG 2c6bcfc0feb3d9d4a57b243fc159a68aa9933f5b
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
test-qwen
new
+1
@@ -0,0 +1 @@
1
+Subproject commit 34c31c0af8fc975140b8c85548fefa1eb7f523e4