Skip to content

GitLab

Commit ff090f36 authored by zhuwenwen's avatar zhuwenwen
Browse files

update flashmla.py

parent 5973c805
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/v1/attention/backends/mla/flashmla.py
View file @ ff090f36
...@@ -167,7 +167,7 @@ class FlashMLAImpl(MLACommonImpl[FlashMLAMetadata]): ...@@ -167,7 +167,7 @@ class FlashMLAImpl(MLACommonImpl[FlashMLAMetadata]):
assert attn_metadata.decode is not None assert attn_metadata.decode is not None
if envs.VLLM_USE_TRITON_CAT: if envs.VLLM_USE_TRITON_CAT:
q = concat_helper([q_nope, q_pe], dim=-1)\ q = concat_helper(q_nope, q_pe, dim=-1)\
.unsqueeze(1) .unsqueeze(1)
else: else:
q = torch.cat([q_nope, q_pe], dim=-1)\ q = torch.cat([q_nope, q_pe], dim=-1)\
......
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