Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
819d548e
Unverified
Commit
819d548e
authored
Apr 09, 2025
by
yihong
Committed by
GitHub
Apr 09, 2025
Browse files
[BugFix] logger is not callable (#16312)
Signed-off-by:
yihong0618
<
zouzou0208@gmail.com
>
parent
477d2a8a
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
vllm/attention/backends/hpu_attn.py
vllm/attention/backends/hpu_attn.py
+2
-2
No files found.
vllm/attention/backends/hpu_attn.py
View file @
819d548e
...
@@ -149,7 +149,7 @@ class HPUAttentionImpl(AttentionImpl, torch.nn.Module):
...
@@ -149,7 +149,7 @@ 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
()
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment