Skip to main content

A benchmarking tool for LM Studio inference

Project description

LM Studio Inference Benchmark

This project provides tools to benchmark inference performance for LM Studio models. It measures various metrics including:

  • Inference latency
  • Tokens per second
  • Memory usage
  • Response generation time

Requirements

  • Python 3.8+
  • LM Studio running locally
  • Required Python packages (see requirements.txt)

Installation

pip install -r requirements.txt

Usage

python main.py --model "your_model_name" --prompt "your_test_prompt"

Features

  • Measures inference latency across different prompt lengths
  • Supports multiple model comparisons
  • Generates detailed performance reports
  • Memory usage tracking
  • Configurable test parameters

License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

benchmarkllm-0.1.0.tar.gz (2.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

benchmarkLLM-0.1.0-py3-none-any.whl (2.8 kB view details)

Uploaded Python 3

File details

Details for the file benchmarkllm-0.1.0.tar.gz.

File metadata

  • Download URL: benchmarkllm-0.1.0.tar.gz
  • Upload date:
  • Size: 2.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for benchmarkllm-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9c3e7b3e92870dc7fddc1eca89886608d875a9a60813c892007d74860eb760cd
MD5 8a2198acaf5da809a230349f776bf359
BLAKE2b-256 e0110749d28ac132ca73fb7eb3f6a55e18efe8499a33435f764c68abc28f242d

See more details on using hashes here.

Provenance

The following attestation bundles were made for benchmarkllm-0.1.0.tar.gz:

Publisher: python-publish.yml on chenyuan99/benchmarkLLM

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file benchmarkLLM-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: benchmarkLLM-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 2.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for benchmarkLLM-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 51ab8150f68834fc0388f8b8652a3945d965584e8bd80ad5e5a3c5c2290fa254
MD5 a2dc68191b68e71adb8354787b922a2c
BLAKE2b-256 d8003abfde88846c94efa3d398874baa0f3f178a44d74fe24115d39209755b97

See more details on using hashes here.

Provenance

The following attestation bundles were made for benchmarkLLM-0.1.0-py3-none-any.whl:

Publisher: python-publish.yml on chenyuan99/benchmarkLLM

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page