Stars
🤗 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.
An Open Source Machine Learning Framework for Everyone
Ongoing research training transformer models at scale
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
A high-throughput and memory-efficient inference and serving engine for LLMs
The official Python library for the OpenAI API
🦜🔗 The platform for reliable agents.
Development repository for the Triton language and compiler
SGLang is a fast serving framework for large language models and vision language models.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…
verl: Volcano Engine Reinforcement Learning for LLMs
Protocol Buffers - Google's data interchange format
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Train transformer language models with reinforcement learning.
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
scikit-learn: machine learning in Python
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
A lightweight LLVM python binding for writing JIT compilers