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
f04d6045
Unverified
Commit
f04d6045
authored
Jun 17, 2025
by
Woosuk Kwon
Committed by
GitHub
Jun 18, 2025
Browse files
[Minor] Zero-initialize attn output buffer (#19784)
Signed-off-by:
Woosuk Kwon
<
woosuk.kwon@berkeley.edu
>
parent
19a53b27
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
vllm/attention/layer.py
vllm/attention/layer.py
+1
-1
No files found.
vllm/attention/layer.py
View file @
f04d6045
...
...
@@ -209,7 +209,7 @@ class Attention(nn.Module):
if
self
.
use_output
:
output_shape
=
(
output_shape
if
output_shape
is
not
None
else
query
.
shape
)
output
=
torch
.
empty
(
output_shape
,
output
=
torch
.
zeros
(
output_shape
,
dtype
=
query
.
dtype
,
device
=
query
.
device
)
hidden_size
=
output_shape
[
-
1
]
...
...
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