mindspore-courses / orange-pi-mindspore
MindSpore notebooks on OrangePi AiPro
☆10Updated 2 weeks ago
Alternatives and similar repositories for orange-pi-mindspore:
Users that are interested in orange-pi-mindspore are comparing it to the libraries listed below
- run ChatGLM2-6B in BM1684X☆49Updated 10 months ago
- A toolbox of yolo models and algorithms based on MindSpore☆119Updated 2 weeks ago
- ☆37Updated 6 months ago
- 模型可视化工具netron的Flask版本☆18Updated 2 years ago
- Run generative AI models in sophgo BM1684X☆155Updated this week
- unify-easy-llm(ULM)旨在打造一个简易的一键式大模型训练工具,支持Nvidia GPU、Ascend NPU等不同硬件以及常用的大模型。☆54Updated 6 months ago
- 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,…☆144Updated 7 months ago
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆41Updated last year
- yolov10 瑞芯微 rknn 板端 C++部署,使用平台 rk3588。☆63Updated 6 months ago
- ☆36Updated 2 months ago
- PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)☆78Updated last week
- This sample shows how to deploy Qwen2 using OpenVINO☆35Updated 4 months ago
- an example of segment-anything infer by ncnn☆121Updated last year
- autoTVM神经网络推理代码优化搜索演示,基于tvm编译开源模型centerface,并使用autoTVM搜索最优推理代码, 最终部署编译为c++代码,演示平台是cuda,可以是其他平台,例如树莓派,安卓手机,苹果手机.Thi is a demonstration of …☆27Updated 3 years ago
- ☆89Updated last week
- Compare multiple optimization methods on triton to imporve model service performance☆48Updated last year
- run chatglm3-6b in BM1684X☆37Updated 10 months ago
- 基于MNN-llm的安卓手机部署大语言模型:Qwen1.5-0.5B-Chat☆63Updated 9 months ago
- TenniS: Tensor based Edge Neural Network Inference System☆13Updated 11 months ago
- 第一章 指针篇 第二章 CUDA原理篇 第三章 CUDA编译器环境配置篇 第四章 kernel函数基础篇 第五章 kernel索引(index)篇 第六章 kenel矩阵计算实战篇 第七章 kenel实战强化篇 第八章 CUDA内存应用与性能优化篇 第九章 CUDA原子(a…☆19Updated 5 months ago
- ncnn和pnnx格式编辑器☆129Updated 3 months ago
- c++实现的clip推理,模型有一点点改动,但是不大,改动和导出模型的代码可以在readme里找到,模型文件都在Releases里,包括AX650的模型。新增支持ChineseCLIP☆29Updated last month
- yolov10 目标检测部署版本,便于移植不同平台(onnx、tensorRT、rknn、Horizon),全网部署最简单、运行速度最快的部署方式(全网首发)。☆48Updated 8 months ago
- Large Language Model Onnx Inference Framework☆28Updated 2 weeks ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆52Updated 2 weeks ago
- PaddlePaddle Code Convert Toolkit. 『飞桨』深度学习代码转换工具☆94Updated 2 weeks ago
- ☆74Updated 5 months ago
- ☆10Updated last month
- 彻底弄懂BP反向传播,15行代码,C++实现也简单,MNIST分类98.29%精度☆34Updated 2 years ago
- ☆17Updated last year