metal

14 projets partagent ce topic GitHub

Les traits relient les membres réellement apparentés entre eux. La taille des points suit les étoiles.

🧬 Membres

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

Open Machine Learning Compiler Framework

high-performance rendering backend (C++, Python, C#, Java)

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

Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.

A high-performance inference engine for AI models

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

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No…

metal-flash-attention

FlashAttention (Metal Port)

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

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache…

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving,…

Core-AI-Framework-Lab

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device…

★ 62 · GitHub ↗

🔗 Familles voisines

vulkan 14 apple-silicon 32 cuda 90 gpu 93 llama-cpp 28 on-device-ai 23 rocm 13 tensor 15

Mesuré à partir des topics GitHub communs aux deux projets, pondérés par leur rareté.