Easy-to-Use C++ Computer Vision Library

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Function unified C/C++ API for running Python functions on desktop, mobile, web, and in the cloud. Register at https://fxn.ai

🔥🔥🔥 A collection of some awesome public NVIDIA CUDA, cuBLAS, cuDNN, TensorRT, AMD ROCm and FPGA projects.

nndeploy是一款模型端到端部署框架。以多端推理以及基于有向无环图模型部署为基础，致力为用户提供跨平台、简单易用、高性能的模型部署体验。

A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.

Efficient CPU/GPU/Vulkan ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet and more!)

ComfyUI Depth Anything Tensorrt Custom Node (up to 5x faster)

Sample apps to demonstrate how to deploy models trained with TAO on DeepStream

Collection of Docker images for ML/DL and video processing projects

deep insight tensorrt

An Alternative for Triton Inference Server. Boosting DL Service Throughput 1.5-4x by Ensemble Pipeline Serving with Concurrent CUDA Streams for PyTorch/LibTorch Frontend and TensorRT/CVCUDA, etc., Backends

Nitro is an C++ inference server on top of TensorRT-LLM. OpenAI-compatible API. Run blazing fast inference on Nvidia GPUs. Used in Jan

Cross-platform, customizable multimedia/video processing framework. With strong GPU acceleration, heterogeneous design, multi-language support, easy to use, multi-framework compatible and high performance, the framework is ideal for transcoding, AI inference, algorithm integration, live video streaming, and more.

Docs for torchpipe: https://github.com/torchpipe/torchpipe

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

C++ object detection inference from video or image input source

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

C++/C TensorRT Inference Example for models created with Pytorch/JAX/TF

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and …