AWS Machine Learning Blog

MAY 2, 2024

Today, we’re excited to announce the availability of Meta Llama 3 inference on AWS Trainium and AWS Inferentia based instances in Amazon SageMaker JumpStart. In this post, we demonstrate how easy it is to deploy Llama 3 on AWS Trainium and AWS Inferentia based instances in SageMaker JumpStart.

AWS 127

AWS ML ML Python 127

AWS Machine Learning Blog

MAY 15, 2024

AWS Graviton3 processors are optimized for ML workloads, including support for bfloat16, Scalable Vector Extension (SVE), and Matrix Multiplication (MMLA) instructions. In this post, we show how to run ONNX Runtime inference on AWS Graviton3-based EC2 instances and how to configure them to use optimized GEMM kernels.

AWS 135

AWS Natural Language Processing Python Deep Learning 135

AWS Machine Learning Blog

APRIL 29, 2024

For AWS and Outerbounds customers, the goal is to build a differentiated machine learning and artificial intelligence (ML/AI) system and reliably improve it over time. First, the AWS Trainium accelerator provides a high-performance, cost-effective, and readily available solution for training and fine-tuning large models.

AWS 126

AWS ML ML Python 126

AWS Machine Learning Blog

DECEMBER 2, 2024

Today at AWS re:Invent 2024, we are excited to announce the new Container Caching capability in Amazon SageMaker, which significantly reduces the time required to scale generative AI models for inference. Container Caching addresses this scaling challenge by pre-caching the container image, eliminating the need to download it when scaling up.

AI 108

AI AI AWS Machine Learning 108

AWS Machine Learning Blog

JANUARY 29, 2025

In this post, we explore how to deploy distilled versions of DeepSeek-R1 with Amazon Bedrock Custom Model Import, making them accessible to organizations looking to use state-of-the-art AI capabilities within the secure and scalable AWS infrastructure at an effective cost. You can monitor costs with AWS Cost Explorer.

AWS 133

AWS ML ML AI 133

AWS Machine Learning Blog

JULY 2, 2024

AWS optimized the PyTorch torch.compile feature for AWS Graviton3 processors. the optimizations are available in torch Python wheels and AWS Graviton PyTorch deep learning container (DLC). The goal for the AWS Graviton team was to optimize torch.compile backend for Graviton3 processors.

AWS 122

AWS Natural Language Processing Python ML 122

IBM Data Science in Practice

APRIL 4, 2023

Introduction This article shows how to monitor a model deployed on AWS Sagemaker for quality, bias and explainability, using IBM Watson OpenScale on the IBM Cloud Pak for Data platform. This article shows how to use the endpoint generated from that tutorial to demonstrate how to monitor the AWS deployment with Watson OpenScale.

AWS 130

AWS Machine Learning Machine Learning Data Science 130

AWS Machine Learning Blog

APRIL 7, 2025

Virginia) AWS Region. Prerequisites To try the Llama 4 models in SageMaker JumpStart, you need the following prerequisites: An AWS account that will contain all your AWS resources. An AWS Identity and Access Management (IAM) role to access SageMaker AI. Access to accelerated instances (GPUs) for hosting the LLMs.

AWS 116

AWS Machine Learning Machine Learning ML 116

IBM Data Science in Practice

MARCH 8, 2023

You can then export the model and deploy it on Amazon Sagemaker on Amazon Web Server (AWS). If you are set up with the required systems, you can download the sample project and complete the steps for hands-on learning. This sample uses the following platforms: Watson Studio and Watson Machine Learning with a Python 3.9

AWS 130

AWS Machine Learning Machine Learning Algorithm 130

AWS Machine Learning Blog

OCTOBER 5, 2023

In this post, we walk through how to fine-tune Llama 2 on AWS Trainium , a purpose-built accelerator for LLM training, to reduce training times and costs. We review the fine-tuning scripts provided by the AWS Neuron SDK (using NeMo Megatron-LM), the various configurations we used, and the throughput results we saw.

AWS 127

AWS Machine Learning Machine Learning Deep Learning 127

AWS Machine Learning Blog

MAY 3, 2023

AWS, Arm, Meta and others helped optimize the performance of PyTorch 2.0 As a result, we are delighted to announce that AWS Graviton-based instance inference performance for PyTorch 2.0 times the speed for BERT, making Graviton-based instances the fastest compute optimized instances on AWS for these models. is up to 3.5

AWS 109

AWS Cloud Computing Python Machine Learning 109

AWS Machine Learning Blog

MAY 1, 2024

Llama2 by Meta is an example of an LLM offered by AWS. To learn more about Llama 2 on AWS, refer to Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart. Virginia) and US West (Oregon) AWS Regions, and most recently announced general availability in the US East (Ohio) Region.

AWS 125

AWS ML ML Clustering 125

AWS Machine Learning Blog

OCTOBER 10, 2023

Customers often need to train a model with data from different regions, organizations, or AWS accounts. Existing partner open-source FL solutions on AWS include FedML and NVIDIA FLARE. These open-source packages are deployed in the cloud by running in virtual machines, without using the cloud-native services available on AWS.

AWS 120

AWS ML ML Algorithm 120

AWS Machine Learning Blog

JANUARY 17, 2024

Today, we’re excited to announce the availability of Llama 2 inference and fine-tuning support on AWS Trainium and AWS Inferentia instances in Amazon SageMaker JumpStart. In this post, we demonstrate how to deploy and fine-tune Llama 2 on Trainium and AWS Inferentia instances in SageMaker JumpStart.

AWS 130

AWS Python Machine Learning Machine Learning 130

AWS Machine Learning Blog

JUNE 23, 2023

Additionally, you can use AWS Lambda directly to expose your models and deploy your ML applications using your preferred open-source framework, which can prove to be more flexible and cost-effective. FastAPI is a modern, high-performance web framework for building APIs with Python. This will be used to deploy our solution.

AWS 101

AWS ML ML Python 101

Flipboard

JUNE 26, 2023

In this post, we look at how we can use AWS Glue and the AWS Lake Formation ML transform FindMatches to harmonize (deduplicate) customer data coming from different sources to get a complete customer profile to be able to provide better customer experience. Run the AWS Glue ML transform job.

AWS 123

AWS ML ML ETL 123

AWS Machine Learning Blog

MAY 4, 2023

AWS has been innovating with purpose-built chips to address the growing need for powerful, efficient, and cost-effective compute hardware. You can use ml.trn1 and ml.inf2 compatible AWS Deep Learning Containers (DLCs) for PyTorch, TensorFlow, Hugging Face, and large model inference (LMI) to easily get started. petaflops for BF16/FP16.

AWS 101

AWS Deep Learning Deep Learning ML 101

AWS Machine Learning Blog

MARCH 8, 2023

This post shows a way to do this using Snowflake as the data source and by downloading the data directly from Snowflake into a SageMaker Training job instance. We create a custom training container that downloads data directly from the Snowflake table into the training instance rather than first downloading the data into an S3 bucket.

ML 133

ML ML AWS Python 133

AWS Machine Learning Blog

MARCH 18, 2025

With this launch, you can now deploy NVIDIAs optimized reranking and embedding models to build, experiment, and responsibly scale your generative AI ideas on AWS. As part of NVIDIA AI Enterprise available in AWS Marketplace , NIM is a set of user-friendly microservices designed to streamline and accelerate the deployment of generative AI.

AWS 108

AWS AI AI Computer Science 108

DrivenData Labs

NOVEMBER 14, 2023

VIIRS' Day/Night Band (DNB) sensor captures nightlight imagery that is useful for mapping populations. ECOSTRESS has been used in the midwestern United States to detects droughts early enough to recover and protect crops.

Python 162

Python AWS Azure Data Analysis 162

AWS Machine Learning Blog

JUNE 4, 2024

Terraform is an IaC tool that allows you to manage AWS resources, software as a service (SaaS) resources, datasets, and more, using declarative configuration. Configure your local Python virtual environment. Download the DialogSum public dataset and convert it to JSONL. python v3.8 Terraform v1.0.0 or newer installed.

AWS 132

AWS Python Artificial Intelligence Artificial Intelligence 132

AWS Machine Learning Blog

MARCH 3, 2025

These recipes include a training stack validated by Amazon Web Services (AWS) , which removes the tedious work of experimenting with different model configurations, minimizing the time it takes for iterative evaluation and testing. Alternatively, you can also use AWS Systems Manager and run a command like the following to start the session.

Clustering 100

Clustering AWS ML ML 100

AWS Machine Learning Blog

JUNE 6, 2023

PyTorch is a machine learning (ML) framework that is widely used by AWS customers for a variety of applications, such as computer vision, natural language processing, content creation, and more. release, AWS customers can now do same things as they could with PyTorch 1.x 24xlarge with AWS PyTorch 2.0 on AWS PyTorch2.0

AWS 97

AWS ML ML Deep Learning 97

PyImageSearch

SEPTEMBER 30, 2024

Home Table of Contents Introduction to GitHub Actions for Python Projects Introduction What Is CICD? For Python projects, CI/CD pipelines ensure that your code is consistently integrated and delivered with high quality and reliability. Git is the most commonly used VCS for Python projects, enabling collaboration and version tracking.

Python 105

Python Deep Learning Deep Learning AWS 105

AWS Machine Learning Blog

MARCH 15, 2024

In addition to Amazon Bedrock, you can use other AWS services like Amazon SageMaker JumpStart and Amazon Lex to create fully automated and easily adaptable generative AI order processing agents. In this post, we show you how to build a speech-capable order processing agent using Amazon Lex, Amazon Bedrock, and AWS Lambda.

AWS 140

AWS AI AI Python 140

AWS Machine Learning Blog

AUGUST 30, 2023

This post demonstrates a strategy for fine-tuning publicly available LLMs for the task of radiology report summarization using AWS services. In the following sections, we demonstrate fine-tuning an LLM available on SageMaker JumpStart for summarization of a domain-specific task via the SageMaker Python SDK. We use an ml.t3.medium

AWS 135

AWS AI AI ML 135

AWS Machine Learning Blog

NOVEMBER 30, 2023

The number of companies launching generative AI applications on AWS is substantial and building quickly, including adidas, Booking.com, Bridgewater Associates, Clariant, Cox Automotive, GoDaddy, and LexisNexis Legal & Professional, to name just a few. Innovative startups like Perplexity AI are going all in on AWS for generative AI.

AWS 145

AWS AI AI ML 145

AWS Machine Learning Blog

APRIL 7, 2023

To reduce the barrier to entry of ML at the edge, we wanted to demonstrate an example of deploying a pre-trained model from Amazon SageMaker to AWS Wavelength , all in less than 100 lines of code. In this post, we demonstrate how to deploy a SageMaker model to AWS Wavelength to reduce model inference latency for 5G network-based applications.

AWS 101

AWS Clustering ML ML 101

Flipboard

MARCH 7, 2023

This post presents and compares options and recommended practices on how to manage Python packages and virtual environments in Amazon SageMaker Studio notebooks. You can manage app images via the SageMaker console, the AWS SDK for Python (Boto3), and the AWS Command Line Interface (AWS CLI). Define a Dockerfile.

Python 123

Python AWS ML ML 123

AWS Machine Learning Blog

SEPTEMBER 20, 2023

For example, you might have acquired a company that was already running on a different cloud provider, or you may have a workload that generates value from unique capabilities provided by AWS. We show how you can build and train an ML model in AWS and deploy the model in another platform.

ML 131

ML ML Azure AWS 131

AWS Machine Learning Blog

MARCH 21, 2023

In addition to the built-in transforms, Data Wrangler contains a custom code editor that allows you to implement custom code written in Python, PySpark, or SparkSQL. This post shows how you can use code stored in AWS CodeCommit in the Data Wrangler custom transform step. Choose Python (PySpark) on the drop-down menu.

AWS 91

AWS Python Machine Learning Machine Learning 91

AWS Machine Learning Blog

MAY 9, 2023

In this post, we help you understand the Python backend that is supported by Triton on SageMaker so that you can make an informed decision for your workloads and achieve great results. Triton supports instance types that support GPUs, CPUs, and AWS Inferentia chips, which allow you to maximize the performance for your workloads.

Python 107

Python ML ML Deep Learning 107

AWS Machine Learning Blog

AUGUST 26, 2024

AWS makes it possible for organizations of all sizes and developers of all skill levels to build and scale generative AI applications with security, privacy, and responsible AI. In this post, we dive into the architecture and implementation details of GenASL, which uses AWS generative AI capabilities to create human-like ASL avatar videos.

AWS 122

AWS AI AI ML 122

AWS Machine Learning Blog

JULY 26, 2023

In this post, we show how you can run Stable Diffusion models and achieve high performance at the lowest cost in Amazon Elastic Compute Cloud (Amazon EC2) using Amazon EC2 Inf2 instances powered by AWS Inferentia2. versions on AWS Inferentia2 cost-effectively. You can run both Stable Diffusion 2.1 The Stable Diffusion 2.1

AWS 98

AWS Deep Learning Deep Learning ML 98

AWS Machine Learning Blog

JULY 2, 2024

AWS Amplify to create and deploy the web application. Amazon API Gateway and AWS Lambda to create an API with an authentication layer and integrate with Amazon Bedrock. The AWS Well-Architected Framework documentation. The Implementing Microservices on AWS whitepaper. Refer to the Amazon Bedrock FAQs for further details.

AWS 142

AWS Artificial Intelligence Artificial Intelligence Database 142

AWS Machine Learning Blog

APRIL 27, 2023

AWS Trainium and AWS Inferentia2 , which are purpose built for DL training and inference, extend their functionality and performance by supporting custom operators (or CustomOps, for short). AWS Neuron , the SDK that supports these accelerators, uses the standard PyTorch interface for CustomOps.

AWS 98

AWS Deep Learning Deep Learning ML 98

AWS Machine Learning Blog

SEPTEMBER 23, 2024

Prerequisties The proposed solution can be implemented in a personal AWS environment using the code that we provide. Before running the labs in this post, ensure you have the following: An AWS account. The appropriate AWS Identity and Access Management (IAM) permissions to access services used in the lab.

AWS 118

AWS Data Scientist Machine Learning Machine Learning 118