vllm-mlx Gajesh2007 · PARTIAL
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.
github.com/Gajesh2007/vllm-mlx · ★ 1 · Forks 0 · Size 10.8 MB
SUMMARY
Technologies 17
Scored 14
Observed 14
Practices 6
Evidence 18
Skips 3
COVERAGE
Analyzed 198 files · 233 commits · 0 API calls
TECHNOLOGIES & DEPTH
JSON LANGUAGE Depth 70
3 files · PRODUCTION
Shell LANGUAGE Depth 70
3 files · PRODUCTION
TOML LANGUAGE Depth 70
2 files · PRODUCTION
Markdown LANGUAGE Depth 70
23 files · PRODUCTION
YAML LANGUAGE Depth 70
2 files · PRODUCTION
Python LANGUAGE Depth 70
156 files · PRODUCTION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
Black QUALITY Depth —
0 files · config only
FastAPI FRAMEWORK Depth 70
3 files · PRODUCTION, TEST
NumPy LIBRARY Depth 81
18 files · PRODUCTION, TEST
Pydantic LIBRARY Depth 70
3 files · PRODUCTION, TEST
Requests LIBRARY Depth 81
13 files · PRODUCTION, TEST
Ruff QUALITY Depth —
0 files · config only
TypeScript LANGUAGE Depth 74
10 files · PRODUCTION
Uvicorn LIBRARY Depth 62
2 files · PRODUCTION
mypy QUALITY Depth —
0 files · config only
pytest TESTING Depth 74
28 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2025-12-06
Last commit 2026-04-25
Active months 5
Commits 233