[2/N][Attention] Enable masked MHA for sparse MLA prefills (#48770)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
co-authored by
OpenAI Codex
parent
864a87febb
commit
82ae4164ee
@@ -39,7 +39,7 @@ else()
|
||||
FetchContent_Declare(
|
||||
vllm-flash-attn
|
||||
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
|
||||
GIT_TAG ed4b7342bc8f0489dd9b649d5288867e35fc6a32
|
||||
GIT_TAG ec4a882d70b19235c824848db944d84a6cb8f9ee
|
||||
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