void-main

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

alpaca-lora

Instruct-tune LLaMA on consumer hardware

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

ChatALL

Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火, 文心一言 and more, discover the best answers

open-gpu-kernel-modules

NVIDIA Linux open GPU kernel module source

flash-attention

Fast and memory-efficient exact attention

triton

Development repository for the Triton language and compiler

nn-zero-to-hero

Neural Networks: Zero to Hero

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

awesome-langchain

😎 Awesome list of tools and projects with the awesome LangChain framework

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

DeepSpeedExamples

Example models using DeepSpeed

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

LookaheadDecoding

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

T3Bench

T3Bench: Benchmarking Current Progress in Text-to-3D Generation

Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

veScale

A PyTorch Native LLM Training Framework

magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch

AI-Software-Startups

A Survey of AI startups

TPAT

TensorRT Plugin Autogen Tool

Pylir

An optimizing ahead-of-time Python Compiler

nccl-fastsocket

NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.

LargeScale

filia

Translate Python and JavaScript into MLIR