0
/ 100
Good community traction and solid fundamentals. Nearly in the top tier.
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.
Top fixes
Highest-impact changes first, ranked by point weight
- 1Tests18pt
Wire your tests to a documented command (e.g. a test script in your build config) so the suite is reproducible.
- 2CI/CD14pt
Add a step like `run: npm test`, `run: pytest`, or `run: tox` to your workflow file.
- 3CI/CD14pt
Add `pull_request:` to the workflow `on:` triggers.
- 4CI/CD14pt
Add a lint step to catch style issues automatically.
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.
Scorecard
Every check, grouped by category and sorted worst-first
Documentation
92
Contributing guide is detailed and thorough.
README is present.
README documents how to install the project.
Licensed under Apache-2.0.
Engineering
63
No linter or formatter config found.
→ Add a linter config such as .eslintrc.json, .prettierrc, ruff.toml, or .golangci.yml to enforce consistent code style.
CI is configured (.github/workflows/release.yml).
Test files detected (scripts/tests).
Lockfile present (tools/test-console/uv.lock). Installs are reproducible.
Issue or PR templates present.
Project health
100
Dependency manifest found (tools/serve-cockpit/pyproject.toml).
Repository has a description.
Actively maintained (pushed within the last month).
.gitignore present.
Repository health signals
Activity, community, and responsiveness at scan time
Activity
- -Commits (30d / 90d)
- 84Forks
- 31Releaseslatest 3mo ago
Community
- -Community health
- -authors own >50% of commits
- 1,521Watchers
Responsiveness
- 1hMedian issue response
- <1hMedian PR merge time
- 11Open issues
Repository files19 root entries
- .githubGood: CI is configured (.github/workflows/release.yml).Good: Issue or PR templates present.
- docs
- lmcache-kv
- models
- results
- scriptsGood: Test files detected (scripts/tests).
- servicesGood: Environment pinned via services/comfyui/Dockerfile.
- toolsGood: Lockfile present (tools/test-console/uv.lock). Installs are reproducible.Good: Dependency manifest found (tools/serve-cockpit/pyproject.toml).
- .dockerignore
- .env.example
- .gitignoreGood: .gitignore present.
- AGENTS.md
- BENCHMARKS.md
- CHANGELOG.md
- CLAUDE.md
- cliff.toml
- CONTRIBUTING.mdGood: Contributing guide is detailed and thorough.Issue: Contributing guide lacks a setup section (−12 pts).Fix: Show new contributors how to get a local dev environment running.Issue: Contributing guide lacks a code style section (−8 pts).Fix: Describe your linting/formatting rules and how to run them.Issue: Contributing guide lacks a testing section (−8 pts).Fix: Show contributors how to run the test suite (e.g. npm test, pytest, cargo test).Good: Contributing guide describes the PR/review workflow.Good: Contributing guide includes code examples.
- LICENSEGood: Licensed under Apache-2.0.
- README.mdGood: 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.Issue: No status badges in the README (−10 pts).Fix: Add CI/build status badges from shields.io or your CI provider to signal project health.Good: README documents how to install the project.Good: README documents how to run the project.
Add this badge to your README
It updates automatically each time the repo is re-graded.
[](https://www.repo-grade.com/report/noonghunna/club-3090)