Skip to content
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.

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

[Benchmark] Unset best_of when running v1 benchmark #14303

Closed
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion benchmarks/backend_request_func.py
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ class RequestFuncInput:
output_len: int
model: str
model_name: Optional[str] = None
best_of: int = 1
best_of: Optional[int] = None if os.environ.get("VLLM_USE_V1", 0) else 1
logprobs: Optional[int] = None
extra_body: Optional[dict] = None
multi_modal_content: Optional[dict] = None
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/benchmark_serving.py
Original file line number Diff line number Diff line change
Expand Up @@ -1084,7 +1084,7 @@ def main(args: argparse.Namespace):
parser.add_argument(
"--best-of",
type=int,
default=1,
default=None if os.environ.get("VLLM_USE_V1", 0) else 1,
help="Generates `best_of` sequences per prompt and "
"returns the best one.",
)
Expand Down