Stars
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
SGLang is a fast serving framework for large language models and vision language models.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
Datasets, Transforms and Models specific to Computer Vision
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
Wan: Open and Advanced Large-Scale Video Generative Models
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
Large Language Model Text Generation Inference
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Low code web framework for real world applications, in Python and Javascript
MicroK8s is a small, fast, single-package Kubernetes for datacenters and the edge.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).
An Autonomous LLM Agent for Complex Task Solving
ModelScope: bring the notion of Model-as-a-Service to life.
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Efficient Triton Kernels for LLM Training
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.