Skip to content

GitLab

Commit ef6c0877 authored by zhuwenwen's avatar zhuwenwen
Browse files

update vllm_flash_attn_varlen_func

parent 2ced1fb2
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/v1/attention/backends/flash_attn.py
View file @ ef6c0877
...@@ -722,6 +722,7 @@ class FlashAttentionImpl(AttentionImpl): ...@@ -722,6 +722,7 @@ class FlashAttentionImpl(AttentionImpl):
# q_descale=layer._q_scale.expand(descale_shape), # q_descale=layer._q_scale.expand(descale_shape),
# k_descale=layer._k_scale.expand(descale_shape), # k_descale=layer._k_scale.expand(descale_shape),
# v_descale=layer._v_scale.expand(descale_shape), # v_descale=layer._v_scale.expand(descale_shape),
is_prefix_cache=False,
) )
return output return output
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment