#metal

QR, symmetric eigendecomposition and SVD for batches of matrices on Apple Silicon GPUs, for MLX and PyTorch. Metal kernels per regime, routed to the GPU or the CPU by policies measured per Mac. C++, Python (pip: metal-linalg, metal-linalg-torch), Swift and C.

Go API client for metal-api

Safe Rust bindings for Apple's Metal framework

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Llama cpp + CapacitorJS support

TypeScript library of 174 research-backed industrial engineering formulas across 14 domains — quality, metallurgy, logistics, safety, machining, and more — with zero dependencies.