Commit b949b805 authored by zhuwenwen's avatar zhuwenwen
Browse files

fix _forward_encoder_attention

parent d10ac4af
......@@ -776,7 +776,7 @@ class FlashAttentionImpl(AttentionImpl):
# q_descale=layer._q_scale.expand(descale_shape),
# k_descale=layer._k_scale.expand(descale_shape),
# v_descale=layer._v_scale.expand(descale_shape),
is_prefix_cache=True,
is_prefix_cache=False,
)
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