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
9c0b1eb5
Unverified
Commit
9c0b1eb5
authored
Oct 20, 2025
by
Chang Su
Committed by
GitHub
Oct 20, 2025
Browse files
[router][grpc] Fix wram-up random token ids for small models (#11887)
parent
01f14a7a
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
9 additions
and
10 deletions
+9
-10
python/sglang/srt/entrypoints/grpc_server.py
python/sglang/srt/entrypoints/grpc_server.py
+9
-10
No files found.
python/sglang/srt/entrypoints/grpc_server.py
View file @
9c0b1eb5
...
...
@@ -998,20 +998,19 @@ def _execute_grpc_server_warmup(
max_new_tokens
=
8
if
is_generation
else
1
if
is_generation
:
# Create tokenized input for warmup
warmup_request_kwargs
=
{
"request_id"
:
f
"WARMUP_
{
time
.
time
()
}
"
,
"tokenized"
:
sglang_scheduler_pb2
.
TokenizedInput
(
input_ids
=
[
954
,
15541
,
2181
,
234
96
,
1476
,
6471
0
,
280
,
],
#
Simple token sequence
original_text
=
"
The capital city of France is
"
,
123
,
456
,
789
,
234
,
567
,
89
0
,
345
,
],
#
Random-looking but safe token IDs
original_text
=
"
warmup request
"
,
),
"sampling_params"
:
sglang_scheduler_pb2
.
SamplingParams
(
temperature
=
0.0
,
...
...
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