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
1a4e4cad
Commit
1a4e4cad
authored
Jun 04, 2025
by
yangql
Browse files
修复qwen3-moe-awq的bug问题
parent
d36deb1a
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
0 deletions
+3
-0
vllm/model_executor/models/qwen3_moe.py
vllm/model_executor/models/qwen3_moe.py
+3
-0
No files found.
vllm/model_executor/models/qwen3_moe.py
View file @
1a4e4cad
...
@@ -332,6 +332,9 @@ class Qwen3MoeModel(nn.Module):
...
@@ -332,6 +332,9 @@ class Qwen3MoeModel(nn.Module):
self
.
padding_idx
=
config
.
pad_token_id
self
.
padding_idx
=
config
.
pad_token_id
self
.
vocab_size
=
config
.
vocab_size
self
.
vocab_size
=
config
.
vocab_size
self
.
config
=
config
self
.
config
=
config
if
self
.
config
.
quantization_config
[
"bits"
]
==
4
:
os
.
environ
[
'LLAMA_NN'
]
=
'0'
os
.
environ
[
'LM_NN'
]
=
'0'
self
.
embed_tokens
=
VocabParallelEmbedding
(
self
.
embed_tokens
=
VocabParallelEmbedding
(
config
.
vocab_size
,
config
.
vocab_size
,
config
.
hidden_size
,
config
.
hidden_size
,
...
...
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