This repository contains SageMaker Samples using ml.inf2 and ml.trn1 instances for machine learning (ML) inference and training workloads on the AWS ML accelerator chips Inferentia and Trainium.
If you have additional SageMaker samples that you would like to contribute to this repository, please submit a pull request following the repository's contribution guidelines.
Samples are organized by use case (training, inference) below:
| Name | Description | Instance Type |
|---|---|---|
| BERT Fine-tuning on SageMaker | Sample training notebook using Hugging Face Trainer API with leveraging Neuron Persistent Cache | Trn1 |
| Name | Description | Instance Type |
|---|---|---|
| BERT Inference on SageMaker | Sample inference notebook using Hugging Face BERT model | Inf2, Trn1, Trn1n |
| Stable Diffusion Inference on SageMaker | How to compile and run HF Stable Diffusion model on SageMaker | Inf2, Trn1, Trn1n |
If you encounter issues with any of the samples in this repository, please open an issue via the GitHub Issues feature.
Please refer to the CONTRIBUTING document for details on contributing additional samples to this repository.
Please refer to the Change Log.