微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

low-latency realtime ASR based on FireRedASR

Turn detection for full-duplex dialogue communication

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

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…

Tongyi Deep Research, the Leading Open-source Deep Research Agent

A flexible and efficient training framework for large-scale alignment tasks

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

SGLang is a fast serving framework for large language models and vision language models.

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

A list of AI autonomous agents

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

Structured Outputs

A high-throughput and memory-efficient inference and serving engine for LLMs

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括303个大模型，覆盖chatgpt、gpt-5、o4-mini、谷歌gemini-2.5、Claude4.5、智谱GLM-Z1、文心一言、qwen3-max、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及kimi-k2、ernie4.5、minimax-M1、DeepSeek-R1-0528、deepsee…

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Retrieval and Retrieval-augmented LLMs

Source code of "Reasons to Reject? Aligning Language Models with Judgments"

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Accelerate inference without tears

Secrets of RLHF in Large Language Models Part I: PPO