iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[perf] wire FA and FlashMLA for sm90 GLM5Next NoPE SparseMLA (#55385)

Browse Source 
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: Leoyzen <leoyzen@gmail.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
This commit is contained in:
Jared Wen
2026-09-22 02:03:59 -07:00
committed by GitHub
co-authored by Kimi Code Leoyzen Lucas Wilkinson
parent 64a48b19b4
commit 91d7324cb1
4 changed files with 225 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmake/external_projects/vllm_flash_attn.cmake
+1 -1
View File
@@ -39,7 +39,7 @@ else()
FetchContent_Declare(
vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG 506341a143fcabd4bb79052a7605ada727d6b3f5
GIT_TAG 9cd61de38763d712bb6ce56e2a02cc2bf718c89f
GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn