aws / aws/sagemaker-pytorch-inference-toolkit
using cuda enabled pytorch image
- 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
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