硬件加速适配

MLX: An array framework for Apple silicon

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

A hardware-accelerated GPU terminal emulator focusing to run in desktops and browsers.

Run LLMs with MLX

A nearly-live implementation of OpenAI's Whisper.

Community maintained hardware plugin for vLLM on Apple Silicon

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

Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.

Node Creative Coding / 3D / Image Processing tool inspired by Quartz Composer

multimedia development kit. download:

W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.