Load EI model to CPU by default in model_fn

aws / sagemaker-pytorch-inference-toolkit

Toolkit for allowing inference and serving with PyTorch on SageMaker. Dockerfiles used for building SageMaker Pytorch Containers are at https://github.com/aws/deep-learning-containers.

Apache License 2.0

134 stars 72 forks source link

Load EI model to CPU by default in model_fn #68

Closed dfan closed 4 years ago

dfan commented 4 years ago

Issue #, if available:

Description of changes: Since the EI-enabled client framework is CPU only, we will load PyTorch models to CPU by default when the user is using Elastic Inference. The model still runs on the server in CUDA

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

sagemaker-bot commented 4 years ago

AWS CodeBuild CI Report

Result: SUCCEEDED
Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

sagemaker-bot commented 4 years ago

AWS CodeBuild CI Report

Result: SUCCEEDED
Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository