一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework

Wan: Open and Advanced Large-Scale Video Generative Models

A lightweight, production-ready C++ library for LLM tokenization, fully compatible with HuggingFace tokenizer.json.

A lightweight, single-header C++11 Jinja2 template engine for LLM chat templates.

A collection of practical, end-to-end AI application examples accelerated by MemryX hardware and software solutions. This repository offers examples for real-time video inference, object detection…

JAX bindings for Flash Attention v2

Tokamax: A GPU and TPU kernel library.

Customizable Reinforcement Learning

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

The repository provides code for running inference with the Meta Segment Anything Model 3 (SAM 3).

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

SAM 3D Objects

Ultralytics YOLO 🚀

The best ChatGPT that $100 can buy.

A Toolkit to Help Optimize Onnx Model

Multi-stream video inference with Ultralytics YOLO - Display multiple video streams in a grid layout with real-time object detection.

🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

A high-performance tool for video upscaling, interpolation, depth estimation, and more. Available as a CLI and Adobe Extension.

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

Use safetensors with ONNX 🤗

mnn tts demo.

mnn asr demo.

llm deploy project based onnx.

caffe model to onnx

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Verifile

。