Skip to content
Merged
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
3 changes: 3 additions & 0 deletions benchmarks/benchmark_latency.py
Original file line number Diff line number Diff line change
Expand Up @@ -189,5 +189,8 @@ def run_to_completion(profile_dir: Optional[str] = None):
)

parser = EngineArgs.add_cli_args(parser)
# V1 enables prefix caching by default which skews the latency
# numbers. We need to disable prefix caching by default.
parser.set_defaults(enable_prefix_caching=False)
args = parser.parse_args()
main(args)
3 changes: 3 additions & 0 deletions vllm/benchmarks/latency.py
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,9 @@ def add_cli_args(parser: argparse.ArgumentParser):
)

parser = EngineArgs.add_cli_args(parser)
# V1 enables prefix caching by default which skews the latency
# numbers. We need to disable prefix caching by default.
parser.set_defaults(enable_prefix_caching=True)
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should this be set to False instead?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, I forgot to revert it back to False after test. Thanks for catching this.
This is PR to fix it. #18771



def main(args: argparse.Namespace):
Expand Down