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
5c7cc33f
Unverified
Commit
5c7cc33f
authored
Aug 06, 2025
by
Yongye Zhu
Committed by
GitHub
Aug 06, 2025
Browse files
[gpt-oss] fix model config with hf_config (#22401)
Signed-off-by:
Yongye Zhu
<
zyy1102000@gmail.com
>
parent
19c9365a
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
vllm/model_executor/models/gpt_oss.py
vllm/model_executor/models/gpt_oss.py
+3
-3
No files found.
vllm/model_executor/models/gpt_oss.py
View file @
5c7cc33f
...
...
@@ -61,9 +61,9 @@ class OAIAttention(nn.Module):
"original_max_position_embeddings"
:
config
.
rope_scaling
[
"original_max_position_embeddings"
],
"beta_fast"
:
config
.
rope_
ntk_beta
,
config
.
rope_
scaling
[
"beta_fast"
]
,
"beta_slow"
:
config
.
rope_
ntk_alpha
,
config
.
rope_
scaling
[
"beta_slow"
]
,
},
is_neox_style
=
True
,
)
...
...
@@ -154,7 +154,7 @@ class MLPBlock(torch.nn.Module):
dtype
=
torch
.
bfloat16
)
assert
config
.
intermediate_size
%
self
.
world_size
==
0
self
.
experts
=
FusedMoE
(
num_experts
=
config
.
num_local_experts
,
top_k
=
config
.
num_experts_per_tok
en
,
top_k
=
config
.
num_experts_per_tok
,
hidden_size
=
config
.
hidden_size
,
intermediate_size
=
config
.
intermediate_size
,
reduce_results
=
True
,
...
...
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