Open Source Computer Vision Library

LLM inference in C/C++

这是一个用于显示当前网速、CPU及内存利用率的桌面悬浮窗软件，并支持任务栏显示，支持更换皮肤。

A brief computer graphics / rendering course

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A C++ header-only HTTP/HTTPS server and client library

Code repository of all OpenGL chapters from the book and its accompanying website https://learnopengl.com

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

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…

Repository for OpenCV's extra modules

Main gperftools repository

Transformer related optimization, including BERT, GPT

High Performance Chinese License Plate Recognition Framework.

剑指Offer——名企面试官精讲典型编程题

Caffe: a fast open framework for deep learning.

A fast single-producer, single-consumer lock-free queue for C++

高性能并行编程与优化 - 课件

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

A machine learning compiler for GPUs, CPUs, and ML accelerators

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

llm deploy project based mnn. This project has merged into MNN.

Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018

works in real-time with detection and recognition accuracy up to 99.8% for Chinese license plates: 100 ms/plate

Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver

Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016