Phoenix8215 / A-White-Paper-on-Neural-Network-Deployment
模型部署白皮书(CUDA|ONNX|TensorRT|C++)🚀🚀🚀
☆167Updated 4 months ago
Alternatives and similar repositories for A-White-Paper-on-Neural-Network-Deployment:
Users that are interested in A-White-Paper-on-Neural-Network-Deployment are comparing it to the libraries listed below
- 【深度学习模型部署框架】支持tf/torch/trt/trtllm/vllm以及更多nn框架,支持dynamic batching、streaming模式,支持python/c++双语言,可限制,可拓展,高性能。帮助用户快速地将模型部署到线上,并通过http/rpc接口方式…☆153Updated 2 weeks ago
- 【高性能OpenAI LLM服务】通过GPRS+TensorRT-LLM+Tokenizers.cpp实现纯C++版高性能OpenAI LLM服务,支持chat和function call模式,支持ai agent,支持分布式多卡推理,支持多模态,支持gradio聊天界面。☆91Updated this week
- 校招、秋招、春招、实习好项目,带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。☆269Updated 2 weeks ago
- A repo that uses TensorRT to deploy wll-trained models.Support RTDETR,YOLO-NAS,YOLOV5,YOLOV6,YOLOV7,YOLOV8,YOLOX.☆105Updated last year
- ☆237Updated 3 months ago
- This repository give a guidline to learn CUDA and TensorRT from the beginning.☆176Updated 7 months ago
- A large number of cuda/tensorrt cases . 大量案例来 学习cuda/tensorrt☆121Updated 2 years ago
- A light llama-like llm inference framework based on the triton kernel.☆78Updated 3 weeks ago
- 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力☆136Updated 6 months ago
- Ai edge toolbox,专门面向边端设备尤其是嵌入式RTOS平台,AI模型部署工具链,包括模型推理引擎和模型压缩工具☆147Updated last year
- 🚀 Do not need libtorch, pure C++ TensorRT deploys SOLOv2 etc, which can be quickly ported to NX/TX2.☆42Updated 2 years ago
- ☆130Updated last year
- 高性能计算课程&CUDA编程实例&深度学习推理框架☆35Updated last year
- Build CUDA Neural Network From Scratch☆16Updated 5 months ago
- learning how CUDA works☆190Updated 5 months ago
- 更友好的nanoGPT的中文教程☆112Updated 8 months ago
- 该代码与B站上的视频 https://www.bilibili.com/video/BV18L41197Uz/?spm_id_from=333.788&vd_source=eefa4b6e337f16d87d87c2c357db8ca7 相关联。☆64Updated last year
- 《CUDA编程基础与实践》一书的代码☆105Updated 2 years ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆213Updated 3 months ago
- 模型压缩的小白入门教程☆226Updated 2 months ago
- CUDA 算子手撕与面试指南☆103Updated 2 weeks ago
- learning-cuda-trt☆107Updated last year
- ☆120Updated last year
- ☆53Updated last year
- An onnx-based quantitation tool.☆71Updated last year
- ☆77Updated last year
- An ultra fast tiny model for lane detection, using onnx_parser, TensorRTAPI, torch2trt to accelerate. our model support for int8, dynamic…☆120Updated 3 years ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆801Updated 2 weeks ago
- ☆258Updated 2 years ago
- b站上的课程☆69Updated last year