风辰的cuda教程

它包含了运行BMF CPU和GPU的完整环境依赖:Cuda11.8, Pytorch 2.0, TensorRT 8.6.1, CV-CUDA 0.3。安装完docker后执行官方教程命令:```shell# 拉取官方镜像docker pull babitmf/bmf_runtime:latest```启动docker环境:```shelldocker run -it babitmf/bmf_runtime:latest bash```编译bmf:```shell./build.sh```## 2、跑通demobmf基于graph的方式组织各个模块,使用下面方式构建graph:```pythonimport bmfgraph ...

(可以按照教程直接使用)Dockerfile 内容:``` FROM paas-cn-beijing.cr.volces.com/cuda/cuda:11.4.3-devel-ubuntu20.04 LABEL org.opencontainers.image.authors="xx@bytedance.com" ENV PATH="/root/miniconda3/bin:${PATH}" ARG DEBIAN_FRONTEND=noninteractive ENV TZ=Europe/Moscow RUN apt-get update && apt-get install -y git ffmpeg li...

(可以按照教程直接使用)Dockerfile 内容:```FROM paas-cn-beijing.cr.volces.com/cuda/cuda:11.4.3-devel-ubuntu20.04LABEL org.opencontainers.image.authors="xx@bytedance.com"ENV PATH="/root/miniconda3/bin:${PATH}"ARG DEBIAN_FRONTEND=noninteractiveENV TZ=Europe/MoscowRUN apt-get update && apt-get install -y git ffmpeg libsm6 libxext6 wget && \ wget https://repo.anaconda.com/miniconda/Minic...