bodza

gguf-tools

GGUF implementation in C as a library and a tools CLI program

flash-attention

Fast and memory-efficient exact attention

metal-flash-attention

FlashAttention (Metal Port)

clinfo

Print all known information about all available OpenCL platforms and devices in the system

applegpuinfo

Print all known information about the GPU on Apple-designed chips

metal-benchmarks

Apple GPU microarchitecture

metal-without-xcode

A command-line-compilable example of Metal.

Alloy

Make usage of Metal API a pleasure

metal-cpp

Metal-cpp is a low-overhead C++ interface for Metal that helps developers add Metal functionality to graphics apps, games, and game engines that are written in C++.

emscripten

Emscripten: An LLVM-to-WebAssembly Compiler

binaryen

Optimizer and compiler/toolchain library for WebAssembly

OpenWorm

Repository for the main Dockerfile with the OpenWorm software stack and project-wide issues

awesome-prompt-injection

Learn about a type of vulnerability that specifically targets machine learning models

kompute

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.

swift

ms-swift: Use PEFT or Full-parameter to finetune 300+ LLMs or 50+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

axolotl

Go ahead and axolotl questions

mlx-swift

Swift API for MLX

mlx

MLX: An array framework for Apple silicon

Ollamac

Mac app for Ollama

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

llama3

The official Meta Llama 3 GitHub site

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

metal_tutorials_youtube

Apple Metal Programming Tutorials

llama.clj

Run LLMs locally. A clojure wrapper for llama.cpp.

text-generation-webui

A Gradio web UI for Large Language Models.

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

matmulfreellm

Implementation for MatMul-free LM.

platonic-rep

tlbrowse

Generate imagined websites on an infinite canvas