mirror of
https://github.com/vllm-project/vllm.git
synced 2026-06-06 00:16:14 +00:00
[Attention] FA4 integration (#32974)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Co-authored-by: Matthew Bonanni <mbonanni@redhat.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
@@ -3,6 +3,8 @@
|
||||
|
||||
# vllm-flash-attn built from source
|
||||
vllm/vllm_flash_attn/*
|
||||
!vllm/vllm_flash_attn/__init__.py
|
||||
!vllm/vllm_flash_attn/flash_attn_interface.py
|
||||
|
||||
# OpenAI triton kernels copied from source
|
||||
vllm/third_party/triton_kernels/*
|
||||
|
||||
Reference in New Issue
Block a user