Large Language Models (LLMs)
Frameworks, tools, and resources for Large Language Models (LLMs), including training, inference (vLLM, llama.cpp), and RAG.
Repositories
xai-org / grok-1
Grok open release
deepseek-ai / DeepSeek-V3
deepseek-ai / DeepSeek-R1
meta-llama / llama
Inference code for Llama models
QwenLM / Qwen3
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
ollama / ollama
Get up and running with Kimi-K2.5, GLM-4.7, DeepSeek, gpt-oss, Qwen, Gemma and other models.
vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
langchain-ai / langchain
🦜🔗 The platform for reliable agents.
run-llama / llama_index
LlamaIndex is the leading framework for building LLM-powered agents over your data.
SillyTavern / SillyTavern
LLM Frontend for Power Users.
oobabooga / text-generation-webui
The definitive Web UI for local AI, with powerful features and easy setup.
open-webui / open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
nomic-ai / gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
huggingface / open-r1
Fully open reproduction of DeepSeek-R1
microsoft / BitNet
Official inference framework for 1-bit LLMs
binary-husky / gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
HKUDS / LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"