biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bug] Fix log issue with \n (#31390)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
Wentao Ye
2025-12-31 00:16:55 -05:00
committed by GitHub
parent 108a2728f7
commit 357d435c54
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/v1/attention/backends/mla/flashmla_sparse.py
View File

@@ -930,8 +930,8 @@ class FlashMLASparseImpl(MLACommonBaseImpl[FlashMLASparseMetadata]):
if self.num_heads % self.padding != 0:
assert self.padding % self.num_heads == 0
logger.warning_once(
f"padding num_heads to {self.padding} \
due to sparse attn kernel requirement"
f"padding num_heads to {self.padding} due to sparse attn "
"kernel requirement"
)
q_padded = q.new_empty((q.shape[0], self.padding, q.shape[2]))
q_padded[:, : self.num_heads, :] = q