iojw

ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

grok-1

Grok open release

ColossalAI

Making large AI models cheaper, faster and more accessible

umami

Umami is a simple, fast, privacy-focused alternative to Google Analytics.

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

uv

An extremely fast Python package installer and resolver, written in Rust.

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

ffmpeg-python

Python bindings for FFmpeg - with complex filtering support

omnivore

Omnivore is a complete, open source read-it-later solution for people who like reading.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

viztracer

VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.

ROCm

AMD ROCm™ Software - GitHub Home

HIP

HIP: C++ Heterogeneous-Compute Interface for Portability

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

promptbench

A unified evaluation framework for large language models

rem

An open source approach to locally record and enable searching everything you view on your Mac.

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

AutoAWQ

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

pdbpp

pdb++, a drop-in replacement for pdb (the Python debugger)

submitit

Python 3.8+ toolbox for submitting jobs to Slurm

lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

MultiModalMamba

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.

arena-hard

Arena-Hard benchmark

LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

foundation-model-stack

🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.

coconet

tensor-trust-data

Dataset for the Tensor Trust project