c_plus_plus

:cow: C++ 记录 :tm: CPP :airplane:

cuda

CUDA NOTE :tm: :rocket:

cv-cuda-dong

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

cvdong

deepstream-yolo

NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

diffusers_dong

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

fastdeploy

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

fastllm_dong

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

infer

A new tensorrt integrate.

lidar_ai_solution

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).

lite.ai.toolkit

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOv5, YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv8. MNN, NCNN, TNN, ONNXRuntime.

nanodet_dong

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

ncnn_deploy

手机端极致优化的高性能神经网络前向计算框架 ncnn :sparkles:

nv_codec

视频编解码: 硬解码多路高并发 CASE :tm: :currency_exchange:

opencv-mobile

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

orange-pi

香橙派5-plus：RK3588 浅入门到深部署 :tm: :jack_o_lantern:

project_template

:information_desk_person: 部署工程模板 :tm:

pybind11_lib

pybind11 — Seamless operability between C++11 and Python :city_sunrise:

sophon_dong

算能芯片部署优化demo

stable-diffusion-webui-tensorrt

TensorRT Extension for Stable Diffusion Web UI

stable-diffusion_dong

stable diffusion Note :alien:

tensorrt-llm

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 efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

tensorrt_pro

C++ library based on tensorrt integration

tpg

A simple tool that can generate TensorRT plugin code quickly.

trt

TensorRT NOTE :tm: :rocket:

trt_pro_learn

对 tensorRT_Pro 开源项目理解 :tm: :cyclone:

video_pipe_c_dong

a plugin-oriented framework for video structured. 国产程序员请加微信zhzhi78拉群交流。

yolo_pruning

模型剪枝 随笔 :tm: :sparkles:

yolov8

YOLOv8 NOTE :tm: :rabbit2:

yolov8_deploy

YOLOv8 C++ DET、SEG、POSE TENSORRT 推理库，便于学习开发拓展与工作中实际部署 :tv: