nvidia/model-optimizer

0

/ 100

Documentation97
Engineering93
Health100
Python2,968Apache-2.01d ago
Grade a repo

A well-known project done right. Strong docs and solid engineering throughout.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

Outstanding. A score of 96/100 puts this repo in a very small tier of truly well-engineered projects.

Documentation

97

Install and run instructions9pt90

README documents how to install the project.

Contributing guide5pt97

Contributing guide is detailed and thorough.

README12pt100

README is present.

License6pt100

Licensed under Apache-2.0.

Engineering

93

Reproducibility6pt80

Lockfile present (uv.lock). Installs are reproducible.

CI/CD14pt85

CI is configured (.github/workflows/_example_tests_runner.yml).

Tests18pt100

Test files detected (.agents/skills/compare-results/tests).

Linting and formatting5pt100

Linter or formatter configured ([tool.ruff] / [tool.black] in pyproject.toml).

Issue and PR templates6pt100

Issue or PR templates present.

Project health

100

Dependency manifest6pt100

Dependency manifest found (pyproject.toml).

Repository metadata5pt100

Repository has a description.

Activity5pt100

Actively maintained (pushed within the last month).

Housekeeping3pt100

.gitignore present.

Repository health signals

Activity, community, and responsiveness at scan time

Activity

  • —
    Commits (30d / 90d)
  • 453
    Forks
  • 37
    Releaseslatest 10mo ago

Community

  • —
    Community health
  • —
    authors own >50% of commits
  • 2,968
    Watchers

Responsiveness

  • 10h
    Median issue response
  • 5d 23h
    Median PR merge time
  • 273
    Open issues
Repository files30 root entries
  • .agents
    Good: Test files detected (.agents/skills/compare-results/tests).
  • .claude
  • .github
    Good: CI is configured (.github/workflows/_example_tests_runner.yml).
    Good: Issue or PR templates present.
  • .gitlab
  • .vscode
  • docs
  • examples
    Good: Environment pinned via examples/vllm_serve/Dockerfile.
  • experimental
  • modelopt
  • modelopt_recipes
  • tests
  • tools
  • .coderabbit.yaml
  • .dockerignore
  • .gitignore
    Good: .gitignore present.
  • .gitmodules
  • .markdownlint-cli2.yaml
  • .pre-commit-config.yaml
  • AGENTS.md
  • CHANGELOG.rst
  • CLAUDE.md
  • CODE_OF_CONDUCT.md
    Good: Code of conduct present.
  • CONTRIBUTING.md
    Good: Contributing guide is detailed and thorough.
    Good: Contributing guide includes setup/install instructions.
    Issue: Contributing guide lacks a code style section (−8 pts).Fix: Describe your linting/formatting rules and how to run them.
    Good: Contributing guide explains how to run tests.
    Good: Contributing guide describes the PR/review workflow.
    Good: Contributing guide includes code examples.
  • LICENSE
    Good: Licensed under Apache-2.0.
  • LICENSE_HEADER
  • noxfile.py
  • pyproject.toml
    Good: Dependency manifest found (pyproject.toml).
  • README.md
    Good: README is present.
    Good: README is well structured with multiple sections.
    Good: README includes screenshots or visuals. Great for first impressions.
    Good: README has code examples.
    Good: README links to a live demo or deployed app.
    Good: README includes status badges.
    Good: README documents how to install the project.
    Good: README documents how to run the project.
  • SECURITY.md
    Good: Security policy present.
  • uv.lock
    Good: Lockfile present (uv.lock). Installs are reproducible.