Skip to content

[benchmark] Update warmup logic for min_tokens and max_tokens #8110

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ZhangYulongg merged 1 commit into from
Aug 21, 2026
+3 −0
Merged

[benchmark] Update warmup logic for min_tokens and max_tokens #8110

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions benchmarks/benchmark_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -443,6 +443,9 @@ async def benchmark(
# warmup短输出：取128和hyper_parameters中max_tokens的最小值
warmup_output_len = min(128, hyper_parameters.get("max_tokens", 128))
warmup_hyper = {k: v for k, v in hyper_parameters.items() if k != "max_tokens"}
# warmup 缩短了 max_tokens，min_tokens 必须一起收敛，否则服务端返回 400
if warmup_hyper.get("min_tokens") is not None:
warmup_hyper["min_tokens"] = min(int(warmup_hyper["min_tokens"]), warmup_output_len)
warmup_request_id = f"warmup_{uuid.uuid4().hex[:8]}"
test_input = RequestFuncInput(
model=model_id,
Expand Down
Loading