开源项目排行榜

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

High Performance Serving Runtime For Interactive Super Intelligence System

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

A framework for efficient model inference with omni-modality models

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

FlashInfer: Kernel Library for LLM Serving

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

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.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

We write your reusable computer vision tools. 💜

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Stable Diffusion web UI

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Learn how to develop, deploy and iterate on production-grade ML applications.

🤗 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.

A deep learning package for many-body potential energy representation and molecular dynamics

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.