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.

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

Jump to bottom

[Misc] add gpu_memory_utilization arg #5079

Merged
merged 2 commits into from
May 29, 2024
Merged

[Misc] add gpu_memory_utilization arg #5079

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
af40344
add gpu_memory_utilization arg
pandyamarut May 28, 2024
d4b1993
reformat
pandyamarut May 28, 2024
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
9 changes: 8 additions & 1 deletion benchmarks/benchmark_latency.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,8 @@ def main(args: argparse.Namespace):
use_v2_block_manager=args.use_v2_block_manager,
enable_chunked_prefill=args.enable_chunked_prefill,
download_dir=args.download_dir,
block_size=args.block_size)
block_size=args.block_size,
gpu_memory_utilization=args.gpu_memory_utilization)

sampling_params = SamplingParams(
n=args.n,
Expand Down Expand Up @@ -211,5 +212,11 @@ def run_to_completion(profile_dir: Optional[str] = None):
type=str,
default=None,
help='Path to save the latency results in JSON format.')
parser.add_argument('--gpu-memory-utilization',
Copy link
Contributor

Choose a reason for hiding this comment

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

Wondering if we want to expose max-model-len as well in the args. We are doing that in the benchmark_througput ( https://sourcegraph.com/github.com/vllm-project/vllm/-/blob/benchmarks/benchmark_throughput.py?L301) and wondering if we should add it here as well since that is another parameter to tune for this error?

type=float,
default=0.9,
help='the fraction of GPU memory to be used for '
'the model executor, which can range from 0 to 1.'
'If unspecified, will use the default value of 0.9.')
args = parser.parse_args()
main(args)
Loading