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
fe36bf5e
Unverified
Commit
fe36bf5e
authored
Jan 18, 2026
by
Canlin Guo
Committed by
GitHub
Jan 18, 2026
Browse files
[Model] Remove the unnecessary dtype conversion in MiniCPM (#32523)
Signed-off-by:
gcanlin
<
canlinguosdu@gmail.com
>
parent
963dc0b8
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
0 additions
and
3 deletions
+0
-3
vllm/model_executor/models/minicpm.py
vllm/model_executor/models/minicpm.py
+0
-3
No files found.
vllm/model_executor/models/minicpm.py
View file @
fe36bf5e
...
...
@@ -300,10 +300,7 @@ class MiniCPMAttention(nn.Module):
)
->
torch
.
Tensor
:
qkv
,
_
=
self
.
qkv_proj
(
hidden_states
)
q
,
k
,
v
=
qkv
.
split
([
self
.
q_size
,
self
.
kv_size
,
self
.
kv_size
],
dim
=-
1
)
orig_dtype
=
q
.
dtype
q
,
k
=
q
.
float
(),
k
.
float
()
q
,
k
=
self
.
rotary_emb
(
positions
,
q
,
k
)
q
,
k
=
q
.
to
(
orig_dtype
),
k
.
to
(
orig_dtype
)
attn_output
=
self
.
attn
(
q
,
k
,
v
)
output
,
_
=
self
.
o_proj
(
attn_output
)
return
output
...
...
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