Mohan Gandhi

Results 11 comments of


Mohan Gandhi

Inference of PyTorch Model when mapped to Elastic Inference Accelarator is 15 times slow as compared to the CPU inference

@Bilal-Yousaf Thanks for reporting this issue. Please refer to Elastic Inference document for recommendation https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html Q: We currently use Amazon Elastic Inference (EI) accelerators. Will we be able to continue...

Increasing the timeout for InvokeEndpoint

SageMaker supports multiple timeout parameters to control the model, container loading and invoke call. ContainerStartupHealthCheckTimeoutInSeconds - helps with container startup health check ModelDataDownloadTimeoutInSeconds - helps with model download timeout (More...

Increasing the timeout for InvokeEndpoint

Reopening the issue as requested. Can you detail the improvement/expectation?

fix: pass code_location to create_model for tensorflow estimator deployment

Can you explain your usecase and add unit/integ test?

How can I use the custom generator to train a TensorFlow model on SageMaker?

We are looking into it.

fix: fixed implementation of fail_on_violation for transform with monitoring

/bot run pr, unit-tests

Support for Hugginface multimodal models

@vincentclaes Please feel free to propose a PR. I don't have a specific code sample; however, consider looking at the new `ModelBuilder` class that has been created to simplify the...

Support for Hugginface multimodal models

More details in the notebook - https://aws.amazon.com/blogs/machine-learning/package-and-deploy-classical-ml-and-llms-easily-with-amazon-sagemaker-part-1-pysdk-improvements/

feature: Add optional CodeArtifact login to FrameworkProcessing job script

@akuma12 Can you rebase your change? I had a brief look and it lgtm. It would be good to get all the test successful.

[Feature Request]: Compile model w/ NEO to target AWS Lambda

@ecurtin2 @j-adamczyk @mvsusp @jorisgu SageMaker support for Serverless inference launched last year https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-endpoints.html Please reopen the issue if you see any issue in using the feature.