Metal

Open Machine Learning Compiler Framework

An open-source cloud-native unified-cloud platform. 开源云原生融合云平台

A high-performance inference engine for AI models

:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placement, measured flag tuni…

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Run large language models locally on Intel Macs with AMD GPUs — native macOS app with Metal acceleration

Apple Silicon mlx with Zero Dependency Java