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
[BugFix] Fix failing gemma-3-1b-it test: `test_lm_eval_accuracy_v1_engine[google/gemma-3-1b-it]` (#27111)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Lucas Wilkinson committed
Oct 18, 2025 at 14:44 UTC
9f020f4f31094d129671037dd65f6b10aae5e814
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 8f468e7da54a8e2f98abfa7c38636aac91c0cba1
41
+ GIT_TAG a893712401d70362fbb299cd9c4b3476e8e9ed54
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