aws / aws/sagemaker-pytorch-inference-toolkit

using cuda enabled pytorch image

Open
#125 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
143
Forks
73
PR merge metrics
No merged PRs in 30d

Description

**What did you find confusing? Please describe.**
kindly tell what is the dockerfile format in order to use cuda/gpu on sagemaker instance, i heard we have to use sagemaker-inference-toolkit , i tried using simple cuda image but its having problem serving
**Describe how documentation can be improved**
there was no examples/samples related to building image with cuda support
**Additional context**
Add any other context or screenshots about the documentation request here.

Contributor guide

Open the contributing guide

Research direction

No file, test, or documentation entry point is named. Start by reading the repository documentation and the linked Deep Learning Containers Dockerfiles, then identify where a CUDA-enabled PyTorch image example belongs; done means users have a documented Dockerfile example and serving guidance for SageMaker GPU instances.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, docker, python, pytorch
Domain
cloud, documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.