[Kernel] Gemma-4 FA4 FP8 Kernel (#48666)
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com> Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com> Co-authored-by: Qixiang Lin <qixiangl@nvidia.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
co-authored by
Qixiang Lin
Claude Opus 4.8
Yongye Zhu
parent
38f097fab8
commit
827a2af806
@@ -39,7 +39,7 @@ else()
|
||||
FetchContent_Declare(
|
||||
vllm-flash-attn
|
||||
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
|
||||
GIT_TAG f3e1a4f74c99145c0717709860bf765de1703779
|
||||
GIT_TAG 617264c1c7955c9e84817654ebeedff069f3c5f1
|
||||
GIT_PROGRESS TRUE
|
||||
# Don't share the vllm-flash-attn build between build types
|
||||
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn
|
||||
|
||||
Reference in New Issue
Block a user