LLM inference in C/C++

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

MyTT将通达信,同花顺,文华麦语言等指标公式,最简移植到Python中,核心库单个文件，仅百行代码,十几个核心函数，神奇的实现所有常见技术指标算法（不依赖talib库）的纯python实现和转换通达信MACD,RSI,BOLL,ATR,KDJ,CCI,PSY等公式,全部基于pandas函数计算方法封装，简洁且高性能，能非常方便的应用在股票指标公式,股市期货量化框架分析,自动程序化交易,数字…

[AAAI2025] SUTrack: Towards Simple and Unified Single Object Tracking

The new home for CnC Tests and Framework Libaries

你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码

ASCII generator (image to text, image to image, video to video)

This is the top-level repository for the Accel-Sim framework.

Optimized primitives for collective multi-GPU communication

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

C++ Linux WebServer服务器

NCCL Tests

CUDA on non-NVIDIA GPUs

使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention

Protocol Buffers - Google's data interchange format

allocation visualization in svg graph

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Examples for HIP

HIP: C++ Heterogeneous-Compute Interface for Portability

[IEEE RA-L'24] Dynamic Obstacle Detection and Tracking (DODT) algorithm for Autonomous Robots (C++/ROS)

[ICCV 2023] OccNet: Scene as Occupancy

🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持流式输出、音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。

This repository give a guidline to learn CUDA and TensorRT from the beginning.

This is a repository to practice multi-thread programming in C++

This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.

🎤 微软语音合成工具，使用 Electron + Vue + ElementPlus + Vite 构建。

(IEEE TIV) A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving

基于live555框架开发的ros2功能包，作为rtsp服务端，推送H264/H265编码视频，客户端可通过url拉取视频。