Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]

Text-audio foundation model from Boson AI

Odoo. Open Source Apps To Grow Your Business.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Enjoy the magic of Diffusion models!

A repository that uses LLMs to evaluate other LLMs in a structured way

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

Nano vLLM

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / Swift / Ultralytics…

A lightweight LMM-based Document Parsing Model

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

Efficient Triton Kernels for LLM Training

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Open-source unified multimodal model

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

开箱即用的基于企业私有知识库的LLM大语言模型的智能客服机器人问答系统，支持私有化部署，代码免费开源且可商用，由芝麻小客服官方推出。

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

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, …

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

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

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

🤗 R1-AQA Model: mispeech/r1-aqa

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs

DeepEP: an efficient expert-parallel communication library

Wan: Open and Advanced Large-Scale Video Generative Models