You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Please add the steps for running GPU docker container in the docker readme. Steps should describe how to specify the gpus to be used on a multi-gpu machine
where device=0,1,2,3 selects GPUs indexed by ordinals 0,1,2 and 3, respectively. torchserve will see only these GPUs. If you specify device=all, then the torchserve will see all the available GPUs.
The text was updated successfully, but these errors were encountered:
I just checked docker/README.md, and it looks like it contains the required examples for GPU usage. @aaronmarkham , I assigned to you so you can verify the content is up to standard - you can close this issue if you're satisfied.
Please add the steps for running GPU docker container in the docker readme. Steps should describe how to specify the gpus to be used on a multi-gpu machine
eg
docker run --rm -it --gpus device=0 -p 8080:8080 -p 8081:8081 torchserve:v0.1-gpu-latest
where device=0,1,2,3 selects GPUs indexed by ordinals 0,1,2 and 3, respectively. torchserve will see only these GPUs. If you specify device=all, then the torchserve will see all the available GPUs.
The text was updated successfully, but these errors were encountered: