- Modify log4j2.xml to remove dependency on javascript.
- add vmargs=-XX:-UseContainerSupport in config
- Update PyTorch Inference toolkit to log telemetry metrics
- pass model directory as input to torchserve
- Update CI to use PyTorch 1.10
- log4j migration from 1 to 2. Replace properties file with xml.
- Enable default model fn for cpu and gpu
- Env variable support for batch inference
- Update TS Archiver to v0.3.1 / Integ tests
- construct correct code path and correctly tar up contents
- Add MMS Config for TS
- Add support for Accept headers with multiple MIME types
- Pin sagemaker dependency version to before version 2
- Change Model server to Torchserve for PyTorch Inference
- add issue templates
- Make docker folder read only, remove unused tests, update reponame, remove incorrect documentation.
- upgrade dependency versions
- Python 3.7 support
- Add code_dir to sys.path in HandlerService for MME
- use tox in buildspec
- Adding Dockerfile for PT1.5
- Install awscli in 1.3.1 eia from pypi instead of conda
- load EI model to CPU by default in model_fn
- Update package versions to fix safety check vulnerabilities
- Change miniconda installation in dockerfiles
- Remove unnecessary dependencies.
- upgrade awscli to fix pip check issue
- upgrade pillow at end of build
- upgrade pillow etc. to fix safety issues in 1.4.0 dockerfiles
- upgrade inference-toolkit version
- install inference toolkit from PyPI.
- Fixed awscli
- awscli update
- Update awscli
- Add multi-model capability label to 1.4.0 Dockerfile
- Upgrade the version of sagemaker-inference
- default model_fn and predict_fn in default handler
- update README with pytorch eia section
- refactor toolkit tests.
- update: Update PyTorch-EI health check binary version to match ECL
- Adding PyTorch EI Support
- undo upgrade mms version and library name
- remove multi-model label from dockerfiles
- Remove torch as requirement for sagemaker_pytorch_inference
- copy all tests to test-toolkit folder.
- Remove awscli pin to avoid broken requirements
- update: Update license URL
- Add release to PyPI. Change package name to sagemaker-pytorch-inference.
- Fix version.
- Fix py2 test environment.
- Adding changes for PyTorch 1.4.0 DLC
- Update artifacts
- Create init.py
- run local GPU tests for Python 3
- update: Update buildspec for PyTorch 1.3.1
- update copyright year in license header
- fix year in copyright license header
- update gitignore
- remove unused test files
- add flake8 check to PR build
- upgrade sagemaker to 1.48.0 for test dependencies
- Updated Pillow version to 6.2.1
- Add LABEL for port bind to 1.2.0 and 1.3.1 dockerfiles
- Updated awscli version
- Added license file
- Disabling logs in deep_learning_container.py
- Wheel name typo fix
- Bump inference-toolkit version and add mme label
- Fix README.
- properly fail build if has-matching-changes fails
- properly fail build if has-matching-changes fails
- upgrade sagemaker-container version
- unmark 2 deploy tests
- update p2 restricted regions
- unmark 2 deploy tests
- update p2 restricted regions
- skip tests in gpu instance restricted regions
- modify buildspecs and tox files
- freeze dependency versions
- add buildspec-release file and upgrade cuda version
- upgrade PyTorch to 1.1
- disable test_mnist_gpu for py2 for now
- fix broken line of buildspec
- prevent hidden errors in buildspec
- Add AWS CodeBuild buildspec for pull request
- Bump minimum SageMaker Containers version to 2.4.6 and pin SageMaker Python SDK to 1.18.16
- fix broken link in README
- Add timeout to test_mnist_gpu test
- Use dummy role in tests and update local failure integ test
- Use the SageMaker Python SDK for local serving integ tests
- Use the SageMaker Python SDK for local integ distributed training tests
- Use the SageMaker Python SDK for local integ single-machine training tests
- Pin fastai version to 1.0.39 in CPU dockerfile
- Use the SageMaker Python SDK for SageMaker integration tests
- Add missing rendering dependencies for opencv and a simple test.
- Add opencv support.
- Freeze PyYAML version to avoid conflict with Docker Compose
- Unfreeze numpy version.
- Freeze TorchVision to 0.2.1
- Specify region when creating S3 resource in integ tests
- Read framework version from Python SDK for integ test default
- Fix unicode display problem in py2 container
- freeze pip <=18.1, fastai == 1.0.39, numpy <= 1.15.4
- Add support for fastai (https://github.com/fastai/fastai) library.
- Remove "requsests" from tests dependencies to avoid regular conflicts with "requests" package from "sagemaker" dependencies.
- Add support for PyTorch-1.0.