20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[BugFix] logger is not callable (#16312)

Browse Source 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
This commit is contained in:
yihong 2025-04-09 15:59:02 +08:00 committed by GitHub
parent 477d2a8aa2
commit 819d548e8a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/attention/backends/hpu_attn.py
View File

@ -149,8 +149,8 @@ class HPUAttentionImpl(AttentionImpl, torch.nn.Module):
self.fused_scaled_dot_product_attention = ModuleFusedSDPA( self.fused_scaled_dot_product_attention = ModuleFusedSDPA(
FusedSDPA) FusedSDPA)
except ImportError: except ImportError:
logger().warning("Could not import HPU FusedSDPA kernel. " logger.warning("Could not import HPU FusedSDPA kernel. "
"vLLM will use native implementation.") "vLLM will use native implementation.")
suppored_head_sizes = HPUPagedAttention.get_supported_head_sizes() suppored_head_sizes = HPUPagedAttention.get_supported_head_sizes()
if head_size not in suppored_head_sizes: if head_size not in suppored_head_sizes: