Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

A high performance, high expansion, easy to use framework for AI application. 为AI应用的开发者提供一套统一的高性能、易用的编程框架，快速基于AI全栈服务、开发跨端边云的AI行业应用，支持GPU，NPU加速。

A library for high performance deep learning inference on NVIDIA GPUs.

Python Single Object Tracking Evaluation

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

Build smaller, faster, and more secure desktop and mobile applications with a web frontend.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

A natural language interface for computers

2021年最新总结，从程序员到CTO，从专业走向卓越，分享大牛企业内部pdf与PPT

A cross-platform video structuring (video analysis) framework. If you find it helpful, please give it a star: ) 跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星 : )

TensorRT+YOLO系列的 多路 多卡 多实例 并行视频分析处理案例

Common utilities for ONNX converters

My TensorRT implimention for [ECCV2018] Distractor-aware Siamese Networks for Visual Object Tracking

A collection of pre-trained, state-of-the-art models in the ONNX format

Actively maintained ONNX Optimizer

Full reimplementation of siamese rpn, has 0.24 eao on vot2017.

CUDA Kernel Benchmarking Library

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

A Toolkit to Help Optimize Large Onnx Model

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

Simplify your onnx model

Simplify your onnx model

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.