Kathryn-cat

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.

the-algorithm

Source code for Twitter's Recommendation Algorithm

llama

Inference code for LLaMA models

text-generation-webui

A Gradio web UI for Large Language Models.

bark

🔊 Text-Prompted Generative Audio Model

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

vllm

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

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

mlc-llm

Universal LLM Deployment Engine with ML Compilation

llama2.c

Inference Llama 2 in one file of pure C

StableLM

StableLM: Stability AI Language Models

LLMsPracticalGuide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

tutorials

PyTorch tutorials.

FasterTransformer

Transformer related optimization, including BERT, GPT

awesome-generative-ai

A curated list of modern Generative Artificial Intelligence projects and services

llm-numbers

Numbers every LLM developer should know

determined

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

awesome-aigc

A list of awesome AIGC works

levanter

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

quantnewgrad2022

adept-inference

Inference code for Persimmon-8B

GPTQ-triton

GPTQ inference Triton kernel

awesome-ai-tools

Finding the AI tools you need!

p1

LLM-based code completion engine

FastGEMV

High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.

CompilerNotes