laya-mlx kuishou68 · PARTIAL
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
github.com/kuishou68/laya-mlx · ★ 0 · Forks 0 · Size 5.8 MB
SUMMARY
Technologies 10
Scored 9
Observed 9
Practices 6
Evidence 11
Skips 1
COVERAGE
Analyzed 130 files · 7 commits · 0 API calls
TECHNOLOGIES & DEPTH
JSON LANGUAGE Depth 70
55 files · PRODUCTION
Markdown LANGUAGE Depth 70
10 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
51 files · PRODUCTION
uv BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 85
21 files · PRODUCTION, TEST
Ruff QUALITY Depth —
0 files · config only
pytest TESTING Depth 74
7 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-09-19
Last commit 2026-09-27
Active months 1
Commits 7