Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
fc42ff7b
Unverified
Commit
fc42ff7b
authored
Aug 08, 2025
by
DarkSharpness
Committed by
GitHub
Aug 08, 2025
Browse files
[Fix] Fix wrong backend chosen in hybrid backend (#8989)
parent
7c0db868
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
6 additions
and
0 deletions
+6
-0
python/sglang/srt/model_executor/model_runner.py
python/sglang/srt/model_executor/model_runner.py
+6
-0
No files found.
python/sglang/srt/model_executor/model_runner.py
View file @
fc42ff7b
...
...
@@ -378,6 +378,12 @@ class ModelRunner:
)
server_args
.
attention_backend
=
"torch_native"
if
server_args
.
prefill_attention_backend
is
not
None
and
(
server_args
.
prefill_attention_backend
==
server_args
.
decode_attention_backend
):
# override the default attention backend
server_args
.
attention_backend
=
server_args
.
prefill_attention_backend
if
server_args
.
attention_backend
is
None
:
"""
Auto select the fastest attention backend.
...
...
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