vllm-project/tpu-inference
Grade a repo

76

/ 100

GradeC

Good shape overall. A few tweaks would push it into the top tier.

Top 38% of 5,156 graded repos

TPU inference for vLLM, with unified JAX and PyTorch support.

Documentation78
Engineering72
Health86
Python364Apache-2.01mo ago

Top fixes

Highest-impact changes first, ranked by point weight

16 to address
  1. 1
    Tests18pt

    Wire your tests to a documented command (e.g. a test script in your build config) so the suite is reproducible.

  2. 2
    CI/CD14pt

    Add a step like `run: npm test`, `run: pytest`, or `run: tox` to your workflow file.

  3. 3
    CI/CD14pt

    Upload coverage to Codecov, Coveralls, or report it with `--coverage` flags.

  4. 4
    README12pt

    Show a quick-start snippet so contributors can see what using your project looks like.

Working through the fixes? Let every push regrade itself.

The free GitHub App rescans this repo on every push and posts the grade as a commit check, so the score climbs without coming back to rescan by hand.

Install the GitHub App

Scorecard

Every check, grouped by category and sorted worst-first

Documentation

78

Install and run instructions9pt45

No install instructions found in the README (−45 pts).

→ Add a section showing how to install dependencies.

README12pt85

README is present.

Contributing guide5pt92

Contributing guide is detailed and thorough.

License6pt100

Licensed under Apache-2.0.

Engineering

72

Linting and formatting5pt0

No linter or formatter configured.

→ Add [tool.ruff] to pyproject.toml. Ruff handles linting and formatting in one tool and replaces flake8, isort, and black.

CI/CD14pt72

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

Tests18pt80

Test files detected (examples/disagg/test_disagg_correctness.py).

Reproducibility6pt80

Lockfile present (requirements.txt). Installs are reproducible.

Issue and PR templates6pt100

Issue or PR templates present.

Project health

86

Dependency manifest6pt55

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)
  • 228
    Forks
  • 8
    Releaseslatest 1mo ago

Community

  • 62% - Fair
    Community health
  • 6 bus factor
    authors own >50% of commits
  • 364
    Watchers

Responsiveness

  • 1d 5h
    Median issue response
  • <1h
    Median PR merge time
  • 322
    Open issues
Repository files27 root entries
  • .buildkite
  • .github
    Good: CI is configured (.github/workflows/check_ready_label.yml).
    Good: Issue or PR templates present.
  • docker
    Good: Environment pinned via docker/Dockerfile.
  • docs
  • examples
    Good: Test files detected (examples/disagg/test_disagg_correctness.py).
  • scripts
  • support_matrices
  • tests
  • tools
  • tpu_inference
  • .coveragerc
  • .dockerignore
  • .gitignore
    Good: .gitignore present.
  • .pre-commit-config.yaml
  • .readthedocs.yaml
  • CONTRIBUTING.md
    Good: Contributing guide is detailed and thorough.
    Good: Contributing guide includes setup/install instructions.
    Good: Contributing guide describes code style expectations.
    Good: Contributing guide explains how to run tests.
    Issue: Contributing guide lacks a PR workflow section (−8 pts).Fix: Explain how to fork, branch, and open a pull request so contributors know what to expect.
    Good: Contributing guide includes code examples.
  • DCO
  • LICENSE
    Good: Licensed under Apache-2.0.
  • MANIFEST.in
  • mkdocs.yml
  • 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.
    Issue: README has no code examples (−15 pts).Fix: Show a quick-start snippet so contributors can see what using your project looks like.
    Good: README links to a live demo or deployed app.
    Good: README includes status badges.
    Issue: No install instructions found in the README (−45 pts).Fix: Add a section showing how to install dependencies.
    Good: README documents how to run the project.
  • requirements_benchmarking.txt
  • requirements_test.txt
  • requirements.txt
    Good: Lockfile present (requirements.txt). Installs are reproducible.
  • setup.py
  • verified_commit_hashes.csv
RepoGrade badge preview

Add this badge to your README

It updates automatically each time the repo is re-graded.

[![RepoGrade](https://www.repo-grade.com/api/badge/vllm-project/tpu-inference)](https://www.repo-grade.com/report/vllm-project/tpu-inference)

More graded Python repos