Skip to content

test: support return logprobs in bench_offline_throughput test #12462

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
merged 2 commits into from
Nov 4, 2025
Merged

test: support return logprobs in bench_offline_throughput test #12462

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
506e591
test: support return logprobs in bench_offline_throughput test
aftersnow Oct 31, 2025
786c586
Update python/sglang/bench_offline_throughput.py
aftersnow Oct 31, 2025
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
26 changes: 25 additions & 1 deletion python/sglang/bench_offline_throughput.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,8 @@ class BenchArgs:
skip_warmup: bool = False
do_not_exit: bool = False
prompt_suffix: str = ""
return_logprob: bool = False
logprob_start_len: int = -1

@staticmethod
def add_cli_args(parser: argparse.ArgumentParser):
Expand Down Expand Up @@ -187,6 +189,17 @@ def add_cli_args(parser: argparse.ArgumentParser):
default="",
help="Suffix applied to the end of all user prompts, followed by assistant prompt suffix.",
)
parser.add_argument(
"--return-logprob",
action="store_true",
help="Enable returning log probabilities.",
)
parser.add_argument(
"--logprob-start-len",
type=int,
default=-1,
help="Start length for logprob. -1 means only return logprobs for output tokens (default). 0 means return logprobs for all tokens including input.",
)

@classmethod
def from_cli_args(cls, args: argparse.Namespace):
Expand All @@ -201,6 +214,8 @@ def throughput_test_once(
ignore_eos: bool,
extra_request_body: Dict,
profile: bool,
return_logprob: bool = False,
logprob_start_len: int = -1,
):
measurement_results = {
"backend": backend_name,
Expand Down Expand Up @@ -233,7 +248,12 @@ def throughput_test_once(
backend.start_profile()

st = time.perf_counter()
gen_out = backend.generate(prompt=prompt, sampling_params=sampling_params)
gen_out = backend.generate(
prompt=prompt,
sampling_params=sampling_params,
return_logprob=return_logprob,
logprob_start_len=logprob_start_len,
)
latency = time.perf_counter() - st

if profile:
Expand Down Expand Up @@ -355,6 +375,8 @@ def throughput_test(
ignore_eos=not bench_args.disable_ignore_eos,
extra_request_body=extra_request_body,
profile=False,
return_logprob=bench_args.return_logprob,
logprob_start_len=bench_args.logprob_start_len,
)
time.sleep(0.5)

Expand All @@ -366,6 +388,8 @@ def throughput_test(
ignore_eos=not bench_args.disable_ignore_eos,
extra_request_body=extra_request_body,
profile=bench_args.profile,
return_logprob=bench_args.return_logprob,
logprob_start_len=bench_args.logprob_start_len,
)
backend.shutdown()

Expand Down
Loading