change: Add default model_fn for cpu and gpu on v1.x

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

change: Add default model_fn for cpu and gpu on v1.x #108

Closed saimidu closed 2 years ago

saimidu commented 3 years ago

Issue #, if available:

Description of changes: Add default_model_fn for CPU/GPU DLCs that use sagemaker-pytorch-inference<2 with multi-model-server

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