Hello_User/gpu-jupyter
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updated to non-docker-compose build and run

Browse Source
This commit is contained in:
Christoph Schranz
2020-07-14 17:11:06 +02:00
parent ffe73f572f
commit 708643b60c
2 changed files with 20 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.build/Dockerfile
View File

@@ -5,6 +5,7 @@
FROM nvidia/cuda:10.1-base-ubuntu18.04
LABEL maintainer="Christoph Schranz <christoph.schranz@salzburgresearch.at>"
# This is a concatenated Dockerfile, the maintainers of subsequent sections may vary.
RUN chmod 1777 /tmp && chmod 1777 /var/tmp
############################################################################
#################### Dependency: jupyter/base-image ########################

26
README.md
View File

@@ -29,7 +29,7 @@ The image of this repository is available on [Dockerhub](https://hub.docker.com/
The CUDA toolkit is not required on the host system, as it will be deployed
in [NVIDIA-docker](https://github.com/NVIDIA/nvidia-docker).
You can be sure that you can access your GPU within Docker,
if the command `docker run --runtime nvidia nvidia/cuda:10.1-base-ubuntu18.04 nvidia-smi`
if the command `docker run --gpus all nvidia/cuda:10.1-base-ubuntu18.04 nvidia-smi`
returns a result similar to this one:
```bash
Mon Jun 22 09:06:28 2020
@@ -58,19 +58,31 @@ The image of this repository is available on [Dockerhub](https://hub.docker.com/
## Quickstart
First of all, it is necessary to generate the `Dockerfile` based on the
First of all, it is necessary to generate the `Dockerfile` based on the NIVIDA base image and the
[docker-stacks](https://github.com/jupyter/docker-stacks).
As soon as you have access to your GPU within Docker containers
(make sure the command `docker run --runtime nvidia nvidia/cuda:10.1-base-ubuntu18.04 nvidia-smi` shows your
GPU statistics), you can generate a Dockerfile and build it via docker-compose.
The two commands will start *GPU-Jupyter* on [localhost:8848](http://localhost:8848) with the default
(make sure the command `docker run --gpus all nvidia/cuda:10.1-base-ubuntu18.04 nvidia-smi` shows your
GPU statistics), you can generate a Dockerfile, build and run it.
The following commands will start *GPU-Jupyter* on [localhost:8848](http://localhost:8848) with the default
password `asdf`.
```bash
./generate-Dockerfile.sh
./start-local.sh -p 8848 # where -p stands for the port, default 8888
./generate_Dockerfile.sh
docker build -t gpu-jupyter .build/ # will take a while
docker run -d -p [port]:8888 gpu-jupyter # starts gpu-jupyter WITHOUT GPU support
```
To run the container with GPU support, a local data volume and , run:
```bash
docker run -d -it --rm --gpus all -p [JUPYTER_PORT]:8888 -v ./data:/home/jovyan/work -e GRANT_SUDO="yes" -e JUPYTER_ENABLE_LAB="yes" gpu-jupyter
```
Or on windows:
```bash
docker run -d -it --rm --gpus all -p [JUPYTER_PORT]:8888 -v /${PWD}/data:/home/jovyan/work -e GRANT_SUDO="yes" -e JUPYTER_ENABLE_LAB="yes" gpu-jupyter
```
## Parameter
The script `generate-Dockerfile.sh` has multiple parameters: