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
1afa9948
Unverified
Commit
1afa9948
authored
Jun 24, 2025
by
Brayden Zhong
Committed by
GitHub
Jun 24, 2025
Browse files
[Llama4] Update `attn_temperature_tuning` (#19997)
Signed-off-by:
Brayden Zhong
<
b8zhong@uwaterloo.ca
>
parent
0d06b533
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
2 deletions
+1
-2
vllm/model_executor/models/llama4.py
vllm/model_executor/models/llama4.py
+1
-2
No files found.
vllm/model_executor/models/llama4.py
View file @
1afa9948
...
...
@@ -148,9 +148,8 @@ class Llama4Attention(nn.Module):
self
.
q_size
=
self
.
num_heads
*
self
.
head_dim
self
.
kv_size
=
self
.
num_kv_heads
*
self
.
head_dim
self
.
scaling
=
self
.
head_dim
**-
0.5
# TODO: attn_temperature_tuning should be a bool in huggingface
self
.
attn_temperature_tuning
=
self
.
nope
and
\
config
.
attn_temperature_tuning
>
0
config
.
attn_temperature_tuning
self
.
floor_scale
=
getattr
(
config
,
"floor_scale"
,
8192.0
)
self
.
attn_scale
=
getattr
(
config
,
"attn_scale"
,
0.1
)
...
...
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