Stars
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
SGLang is a fast serving framework for large language models and vision language models.
The definitive Web UI for local AI, with powerful features and easy setup.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Build resilient language agents as graphs.
Supercharge Your LLM Application Evaluations 🚀
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Graph Neural Network Library for PyTorch
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
A library for efficient similarity search and clustering of dense vectors.
Large Language Model Text Generation Inference
LlamaIndex is the leading framework for building LLM-powered agents over your data.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
✨✨Latest Advances on Multimodal Large Language Models
Gemma open-weight LLM library, from Google DeepMind
Fast and memory-efficient exact attention
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A collection of AWESOME things about Graph-Related LLMs.
Notes for papers presented during our paper reading sessions
A list of all "all you need" papers. Updated daily using the arXiv API.
Tabular Deep Learning Library for PyTorch
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…
Hackable and optimized Transformers building blocks, supporting a composable construction.