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
131
stars
70
forks
source link
Cleanup to remove EIA integration tests and other unused files/code #158
The objective of this PR is to cleanup the PyTorch inference toolkit to remove EIA integration tests and other unused files/code. The following need to be removed/modified:
The following need to be removed from the PyTorch inference toolkit:
Issue #, if available:
Description of changes:
The objective of this PR is to cleanup the PyTorch inference toolkit to remove EIA integration tests and other unused files/code. The following need to be removed/modified:
The following need to be removed from the PyTorch inference toolkit:
artifacts
directory.docker
directory.test/container
. Specifically, we removed the directories corresponding to versions1.3.1
,1.5.0
,1.6.0
and1.10.2
.test_default_inference_eia()
and any dependencies it requires. Removed any code related toaccelerator_type
.test_mnist_eia()
and any dependencies it requires. Removed any code related toaccelerator_type
.default_model_eia
.model_eia
.accelerator_type
..flake8
to includesagemaker_inference
in import sequence.MANIFEST.in
to recursively includesrc/sagemaker_inference/*
.README.rst
file to no longer reference dependency on base inference toolkit.By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.