[Attention] Enable masked MHA for GLM-5 head dimensions (#53785)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Matthew Bonanni
2026-08-27 21:17:12 +00:00
committed by GitHub
co-authored by OpenAI Codex
parent 3a9bfc209f
commit de9250ac9e
10 changed files with 527 additions and 74 deletions
@@ -39,7 +39,7 @@ else()
FetchContent_Declare(
vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG 4eb29359a51b4fe67c8c0f0c5e931236971aa492
GIT_TAG 06bdd47c0d0383daf6a2ff0c418faff9c6da16e5
GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn