mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Starred 29 days ago
AI Analysis
Intermediate
Analyzed Sep 23, 2026
Quality Score
80/100
Activity
unknown
Category
library
Tokens
8,852
80
/ 100
Excellent Quality
Based on AI analysis
A high-performance Python library providing a native MLX runtime for Laya typed decision models, enabling sub-15ms local inference on Apple Silicon without external dependencies like PyTorch or cloud APIs.
Date: Sep 23, 2026
Version: v1
Tokens: 8,852
Cost: $4.0000
Stats
Stars
Starred by users
Forks
Repository forks
Watchers
Watching this repo
Issues & Pull Requests
Quick Browse
Repository
VisibilityPublic
CreatedSep 19, 2026
Size~
Releases
0 releases totalView all