Update sgl-attn to include SWA decode optimizations (#19655)
This commit is contained in:
@@ -92,7 +92,7 @@ FetchContent_Populate(repo-flashinfer)
|
||||
FetchContent_Declare(
|
||||
repo-flash-attention
|
||||
GIT_REPOSITORY https://github.com/sgl-project/sgl-attn
|
||||
GIT_TAG cc75c5c5979a607ad20a6828635646f9841acf01
|
||||
GIT_TAG bcf72ccc6816b36a5fae2c5a3c027604629785e0
|
||||
GIT_SHALLOW OFF
|
||||
)
|
||||
FetchContent_Populate(repo-flash-attention)
|
||||
|
||||
Reference in New Issue
Block a user