Pick the right ML services and frameworks to support your work
Introduction
At its most basic, machine learning (ML) is designed to provide digital tools and services to learn from data, identify patterns, make predictions, and then act on those predictions. Almost all artificial intelligence (AI) systems today are created using ML. ML uses large amounts of data to create and validate decision logic. This decision logic forms the basis of the AI model.
Scenarios where AWS machine learning services may be applied include:
- Specific use cases - AWS machine learning services can support your AI powered use cases with a broad range of pre-built algorithms, models, and solutions for common use cases and industries. You have a choice of 23 pre-trained services, including Amazon Personalize, Amazon Kendra, and Amazon Monitron.
- Customizing and scaling machine learning - Amazon SageMaker is designed to help you build, train, and deploy ML models for any use case. You can build your own or access open source foundational models on AWS through Amazon SageMaker and Amazon Bedrock.
- Accessing specialized infrastructure - Use the ML frameworks and infrastructure provided by AWS when you require even greater flexibility and control over your machine learning workflows, and are willing to manage the underlying infrastructure and resources yourself.
This decision guide will help you ask the right questions, evaluate your criteria and business problem, and determine which services are the best fit for your needs.
Rajneesh Singh, general manager of Amazon SageMaker Low-Code/No-Code team at AWS, explains how machine learning can address business problems.
Purpose
Help determine which AWS ML services are the best fit for your needs.
Last updated
May 3, 2024
Understand
As organizations continue to adopt AI and ML technologies, the importance of understanding and choosing among AWS ML services is an on-going challenge.
- At a high level, artificial intelligence is a way to describe any system that can replicate tasks that previously required human intelligence. Most AI use cases are looking for a probabilistic outcome—making a prediction or decision with a high degree of certainty, similar to human judgement.
- Almost all AI systems today are created using machine learning. ML uses large amounts of data to create and validate decision logic, which is known as a model.
- Classification AI is a subset of ML that recognizes patterns to identify something. Predictive AI is a subset of ML that predicts future trends based on statistical patterns an historical data.
- Finally, generative AI is a subset of deep learning that can create new content and ideas, like conversations, stories, images, videos, and music. Generative AI is powered by very large models that are pretrained on vast corpora of data, called the Foundation Models or FMs. Amazon Bedrock is a fully managed service that offers a choice of high-performing FMs for building and scaling generative AI applications. Amazon Q Developer and Amazon Q Business are generative-AI powered assistants for specific use cases.
This guide is designed primarily to cover services in the Classification AI and Predictive AI machine learning categories.
In addition, AWS offers specialized, accelerated hardware for high performance ML training and inference.
- Amazon EC2 P5 instances are equipped with NVIDIA H100 Tensor Core GPUs, which are well-suited for both training and inference tasks in machine learning. Amazon EC2 G5 instances feature up to 8 NVIDIA A10G Tensor Core GPUs, and second generation AMD EPYC processors, for a wide range of graphics-intensive and machine learning use cases.
- AWS Trainium is the second-generation ML accelerator that AWS has purpose-built for deep learning (DL) training of 100B+ parameter models.
- AWS Inferentia2-based Amazon EC2 Inf2 instances are designed to deliver high performance at the lowest cost in Amazon EC2 for your DL and generative AI inference applications.
Consider
When solving a business problem with AWS ML services, consideration of several key criteria can help ensure success. The following section outlines some of the key criteria to consider when choosing a ML service.
-
Problem definition
-
ML algorithm
-
Security
-
Latency
-
Accuracy
-
AWS and Responsible AI
-
The first step in the ML lifecycle is to frame the business problem. Understanding the problem you are trying to solve is essential for choosing the right AWS ML service, as different services are designed to address different problems. It is also important to determine whether ML is the best fit for your business problem.
Once you have determined that ML is the best fit, you can start by choosing from a range of purpose-built AWS AI services (in areas such as speech, vision and documents).
Amazon SageMaker provides fully managed infrastructure if you need to build and train your own models. AWS offers an array of advanced ML frameworks and infrastructure choices for the cases where you require highly customized and specialized ML models. AWS also offers a broad set of popular foundation models for building new applications with generative AI.
-
Choosing the ML algorithm for the business problem you are trying to solve depends on the type of data you are working with, as well as the desired outcomes. The following information outlines how each of the major AWS AI/ML service categories empowers you to work with its algorithms:
- Specialized AI services: These services offer a limited ability to customize the ML algorithm, as they are pre-trained models optimized for specific tasks. You can typically customize the input data and some parameters, but do not have access to the underlying ML models or the ability to build your own models.
- Amazon SageMaker: This service provides the most flexibility and control over the ML algorithm. You can use SageMaker to build custom models using your own algorithms and frameworks, or use pre-built models and algorithms provided by AWS. This allows for a high degree of customization and control over the ML process.
- Lower-level ML frameworks and infrastructure: These services offer the most flexibility and control over the ML algorithm. You can use these services to build highly customized ML models using their own algorithms and frameworks. However, using these services requires significant ML expertise and may not be feasible for all every use case.
-
If you need a private endpoint in your VPC, your options will vary based on the layer of AWS ML services you are using. These include:
- Specialized AI services: Most specialized AI services do not currently support private endpoints in VPCs. However, Amazon Rekognition Custom Labels and Amazon Comprehend Custom can be accessed using VPC endpoints.
- Core AI services: Amazon Translate, Amazon Transcribe, and Amazon Comprehend all support VPC endpoints.
- Amazon SageMaker: SageMaker provides built-in support for VPC endpoints, allowing you to deploy their trained models as an endpoint accessible only from within their VPC.
- Lower-level ML frameworks and infrastructure: You can deploy your models on Amazon EC2 instances or in containers within your VPC, providing complete control over the networking configuration.
-
Higher-level AI services, such as Amazon Rekognition and Amazon Transcribe, are designed to handle a wide variety of use cases and offer high performance in terms of speed. However, they might not meet certain latency requirements.
If you are using lower-level ML frameworks and infrastructure, we recommended leveraging Amazon SageMaker. This option is generally faster than building custom models due to its fully managed service and optimized deployment options. While a highly optimized custom model may outperform SageMaker, it will require significant expertise and resources to build.
-
The accuracy of AWS ML services varies based on the specific use case and level of customization required. Higher-level AI services, such as Amazon Rekognition, are built on pre-trained models that have been optimized for specific tasks and offer high accuracy in many use cases.
In some cases, you can choose to use Amazon SageMaker, which provides a more flexible and customizable platform for building and training custom ML models. By building your own models, you may be able to achieve even higher accuracy than what is possible with pre-trained models.
You can also choose to use ML frameworks and infrastructure, such as TensorFlow and Apache MXNet, to build highly customized models that offer the highest possible accuracy for your specific use case.
-
AWS builds foundation models (FMs) with responsible AI in mind at each stage of its development process. Throughout design, development, deployment, and operations we consider a range of factors including:
- Accuracy (how closely a summary matches the underlying document; whether a biography is factually correct)
- Fairness, (whether outputs treat demographic groups similarly)
- Intellectual property and copyright considerations
- Appropriate usage (filtering out user requests for legal advice, or medical diagnoses, or illegal activities)
- Toxicity (hate speech, profanity, and insults)
- Privacy (protecting personal information and customer prompts)
AWS builds solutions to address these issues into the processes used for acquiring training data, into the FMs themselves, and into the technology used to pre-process user prompts and post-process outputs.
Choose
Now that you know the criteria by which you will be evaluating your ML service options, you are ready to choose which AWS ML service is right for your organizational needs.
The following table highlights which ML services are optimized for which circumstances. Use it to help determine the AWS ML service that is the best fit for your use case.
These artificial intelligence services are intended to meet specific needs. They include personalization, forecasting, anomaly detection, speech transcription, and others. Since they are delivered as services, they can be embedded into applications without requiring any ML expertise.
Amazon Augmented AI (Amazon A2I) enables you to build the workflows required for human review of ML predictions. Amazon A2I is designed to bring human review to all developers, removing the undifferentiated heavy lifting associated with building human review systems or managing large numbers of human reviewers.
Amazon CodeGuru is designed to provide intelligent recommendations for improving application performance, efficiency, security, and code quality.
Amazon Comprehend allows you to do natural language processing tasks, such as sentiment analysis, entity recognition, topic modeling, and language detection, on your text data.
Amazon Comprehend Medical
Amazon Comprehend Medical detects and returns useful information in unstructured clinical text such as physicians notes, discharge summaries, test results, and case notes. It uses natural language processing (NLP) models to detect entities, which are textual references to medical information such as medical conditions, medications, or Protected Health Information (PHI).
Amazon DevOps Guru generates operational insights using machine learning to help you improve the performance of your operational applications.
Amazon Forecast is a fully managed deep learning service for time-series forecasting. By providing Amazon Forecast with historical time-series data, you can predict future points in the series. Time-series forecasting is useful in multiple domains, including retail, financial planning, supply chain, and healthcare. You can also use Amazon Forecast to forecast operational metrics for inventory management, and workforce and resource planning and management.
Amazon Kendra is a search service, powered by machine learning, that helps your users to search unstructured text using natural language.
Amazon Lex helps you build chatbots and voice assistants that can interact with users in a natural language interface. It provides pre-built dialog management, language understanding, and speech recognition capabilities.
AWS Panorama is a service that brings computer vision to your on-premises camera network. You install the AWS Panorama Appliance or another compatible device in your datacenter, register it with AWS Panorama, and deploy computer vision applications from the cloud. AWS Panorama works with your existing real time streaming protocol (RTSP) network cameras.
Amazon Personalize is a fully managed machine learning service that uses your data to generate item recommendations for your users. It can also generate user segments based on the users' affinity for certain items or item metadata.
Use Amazon Polly to convert text into lifelike speech, making it easier to create voice-enabled applications and services.
Amazon Rekognition helps you analyze images, faces and videos, detect objects, and text within them.
Amazon Textract helps you extract text and data from scanned documents, forms, and tables, making it easier to store, analyze, and manage such data.
Amazon Transcribe allows you to automatically transcribe audio and video recordings into text. This can save time and effort compared to manual transcription.
Use this service to translate text from one language to another in real-time. This is particularly helpful if your business operates in multiple countries or needs to communicate with non-native speakers.
These services can be used to develop customized machine learning models or workflows that go beyond the pre-built functionalities offered by the core AI services.
Amazon SageMaker is a fully managed machine learning service. It includes a broad set of tools designed to enable high-performance, low-cost machine learning.
SageMaker JumpStart provides pretrained, open-source models for a wide range of problem types to help you get started with machine learning. You can incrementally train and tune these models before deployment. JumpStart also provides solution templates that set up infrastructure for common use cases, and executable example notebooks for machine learning with SageMaker.
A fully integrated development environment (IDE) that enables developers to build, train, and deploy machine learning models at scale. It provides a single web-based interface to manage the entire machine learning lifecycle, from data preparation and model training to deployment and monitoring. SageMaker Studio also supports popular tools like Jupyter notebooks, Git, and TensorFlow, and offers a suite of pre-built algorithms for common use cases.
visual interface for building, editing, and running machine learning workflows. It allows developers to drag-and-drop components to create end-to-end workflows that automate data processing, feature engineering, model training, and deployment. SageMaker Canvas also provides real-time feedback on the performance of each component, enabling developers to optimize their workflows for speed and accuracy.
A cloud-based IDE for learning and experimenting with machine learning using pre-built Jupyter notebooks. It provides a low-cost, low-risk environment for developers to explore and experiment with machine learning algorithms and models. SageMaker Studio Lab includes a range of pre-built notebooks covering topics like image recognition, natural language processing, and anomaly detection.
A managed service for labeling data to train and improve machine learning models. It provides a highly accurate and efficient way to label large datasets by using a combination of human annotators and machine learning algorithms. SageMaker Ground Truth supports a wide range of data types, including text, image, video, and audio, and integrates seamlessly with other SageMaker services for end-to-end machine learning workflows.
An open-source machine learning framework that offers dynamic computation graphs and automatic differentiation for building and training neural networks. PyTorch is known for its ease of use and flexibility, and has a large and active community of developers contributing to its development.
An open-source deep learning framework that supports multiple programming languages, including Python, Scala, and R. MXNet is known for its scalability and speed, and offers a range of high-level APIs for building and training neural networks, as well as low-level APIs for advanced users.
Hugging Face on Amazon SageMaker
An open-source library for natural language processing (NLP) that provides a wide range of pre-trained models and tools for working with text data. Hugging Face is known for its ease of use and high performance, and is widely used for tasks such as text classification, sentiment analysis, and language translation.
An open-source machine learning framework developed by Google that is widely used for building and training neural networks. TensorFlow is known for its scalability, speed, and flexibility, and supports a range of programming languages including Python, C++, and Java. TensorFlow offers a wide range of pre-built models and tools for image and text processing, as well as low-level APIs for advanced users who require greater control over their models.
To deploy machine learning in production, you need cost-effective infrastructure, which Amazon enables with AWS-built silicon.
AWS Trainium is the second-generation machine learning (ML) accelerator that AWS purpose built for deep learning training of 100B+ parameter models. Each Amazon Elastic Compute Cloud (EC2) Trn1 instance deploys up to 16 AWS Trainium accelerators to deliver a high-performance, low-cost solution for deep learning (DL) training in the cloud.
AWS Inferentia and AWS Inferentia2
The first-generation AWS Inferentia accelerator powers Amazon Elastic Compute Cloud (Amazon EC2) Inf1 instances, which deliver up to 2.3x higher throughput and up to 70% lower cost per inference than comparable Amazon EC2 instances. AWS Inferentia2 accelerator delivers a major leap in performance and capabilities over first-generation AWS Inferentia. Inferentia2 delivers up to 4x higher throughput and up to 10x lower latency compared to Inferentia.
Designed to help you provision resilient clusters for running machine learning workloads and developing state-of-the-art models such as large language models (LLMs), diffusion models, and foundation models (FMs).
These tools and associated services are designed to help you ease deployment of machine learning.
These Amazon Machine Images (AMIs) are designed to help you accelerate deep learning in the cloud.
A set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.
A service designed to help you match, link, and enhance related records stored across multiple applications, channels, and data stores.
Use
Now that you have a clear understanding of the criteria you need to apply in choosing an AWS ML service, you can select which AWS AI/ML service(s) are optimized for your business needs.
To explore how to use and learn more about the service(s) you have chosen, we have provided three sets of pathways to explore how each service works. The first set of pathways provides in-depth documentation, hands-on tutorials, and resources to get started with Amazon Comprehend, Amazon Textract, Amazon Translate, Amazon Lex, Amazon Polly, Amazon Rekognition, and Amazon Transcribe.
-
Amazon Comprehend
-
Amazon Textract
-
Amazon Translate
-
Amazon Lex
-
Amazon Polly
-
Amazon Rekognition
-
Amazon Transcribe
-
Amazon Comprehend
-
Get started with Amazon Comprehend
Use the Amazon Comprehend console to create and run an asynchronous entity detection job.
Get started with the tutorial »Analyze insights in text with Amazon Comprehend
Learn how to use Amazon Comprehend to analyze and derive insights from text.
Amazon Comprehend Pricing
Explore information on Amazon Comprehend pricing and examples. -
Amazon Textract
-
Getting Started with Amazon Textract
Learn how Amazon Textract can be used with formatted text to detect words and lines of words that are located close to each other, as well as analyze a document for items such as related text, tables, key-value pairs, and selection elements.
Extract text and structured data with Amazon Textract
Learn how to use Amazon Textract to extract text and structured data from a document.
AWS Power Hour: Machine Learning
Dive into Amazon Textract in this episode, spend time in the AWS Management Console, and review code samples that will help you understand how to make the most of service APIs.
-
Amazon Translate
-
Getting started with Amazon Translate using the console
The easiest way to get started with Amazon Translate is to use the console to translate some text. Learn how to translate up to 10,000 characters using the console.
Translate Text Between Languages in the Cloud
In this tutorial example, as part of an international luggage manufacturing firm, you need to understand what customers are saying about your product in reviews in the local market language - French.
Amazon Translate pricing
Explore Amazon Translate pricing, including Free Tier - which provides 2 million characters per month for 12 months.
Explore the guide »
Accelerate multilingual workflows with a customizable translation solution
Explore how to build a unified translation solution with customization features using Amazon Translate and other AWS services.
-
Amazon Lex
-
Amazon Lex V2 Developer Guide
Explore information about getting started, how it works, and pricing information for Amazon Lex V2.
Explore the guide »Introduction to Amazon Lex
We introduce you to the Amazon Lex conversational service, and walk you through examples that show you how to create a bot and deploy it to different chat services.Take the course » (sign-in required)
Exploring Generative AI in conversational experiences
Explore the use of generative AI in conversation experiences.
-
Amazon Polly
-
What is Amazon Polly?
Explore a complete overview of the cloud service that converts text into lifelike speech, and can be used to develop applications to increase your customer engagement and accessibility.Highlight text as it’s being spoken using Amazon Polly
We introduce you to approaches for highlighting text as it’s being spoken to add visual capabilities to audio in books, websites, blogs, and other digital experiences.Create audio for content in multiple languages with the same TTS voice persona in Amazon Polly
We explain Neural Text-to-Speech (NTTS) and discuss how a broad portfolio of available voices, providing a range of distinct speakers in supported languages, can work for you.
-
Amazon Rekognition
-
What is Amazon Rekognition?
Explore how you can use this service to add image and video analysis to your applications.Hands-on Rekognition: Automated Image and Video Analysis
Learn how facial recognition works with streaming video, along with code examples and key points at a self-guided pace.
Amazon Rekognition FAQs
Learn the basics of Amazon Rekognition and how it can help you improve your deep learning and visually analyze your applications. -
Amazon Transcribe
-
What is Amazon Transcribe?
Explore the AWS automatic speech recognition service using ML to convert audio to text. Learn how to use this service as a standalone transcription or add speech-to-text capability to any application.Amazon Transcribe Pricing
We introduce you to the AWS pay-as-you-go transcription, including custom language model options and the Amazon Transcribe Free Tier.Create an audio transcript with Amazon Transcribe
Learn how to use Amazon Transcribe to create a text transcript of recorded audio files using a real-world use case scenario for testing against your needs.
Build an Amazon Transcribe streaming app
Learn how to build an app to record, transcribe, and translate live audio in real-time, with results emailed directly to you.
The second set of AI/ML AWS service pathways provide in-depth documentation, hands-on tutorials, and resources to get started with the services in the Amazon SageMaker family.
-
SageMaker
-
SageMaker Autopilot
-
SageMaker Canvas
-
SageMaker Data Wrangler
-
SageMaker Ground Truth/Ground Truth Plus
-
SageMaker JumpStart
-
SageMaker Pipelines
-
SageMaker Studio
-
SageMaker
-
How Amazon SageMaker works
Explore the overview of machine learning and how SageMaker works.Getting started with Amazon SageMaker
Learn how to join an Amazon SageMaker Domain, giving you access to Amazon SageMaker Studio and RStudio on SageMaker.
Explore the guide »Use Apache Spark with Amazon SageMaker
Learn how to use Apache Spark for preprocessing data and SageMaker for model training and hosting.
Explore the guide »Use Docker containers to build models
Explore how Amazon SageMaker makes extensive use of Docker containers for build and runtime tasks. Learn how to deploy the pre-built Docker images for its built-in algorithms and the supported deep learning frameworks used for training and inference.
Explore the guide »
Machine learning frameworks and languages
Learn how to get started with SageMaker using the Amazon SageMaker Python SDK. -
SageMaker Autopilot
-
Create an Amazon SageMaker Autopilot experiment for tabular data
Learn you how to create an Amazon SageMaker Autopilot experiment to explore, pre-process, and train various model candidates on a tabular dataset.Automatically create machine learning models
Learn how to use Amazon SageMaker Autopilot to automatically build, train, and tune a ML model, and deploy the model to make predictions.
Explore modeling with Amazon SageMaker Autopilot with these example notebooks
Explore example notebooks for direct marketing, customer churn prediction and how to bring your own data processing code to Amazon SageMaker Autopilot. -
SageMaker Canvas
-
Get started using Amazon SageMaker Canvas
Learn how to get started with using SageMaker Canvas.Generate machine learning predictions without writing code
This tutorial explains how to use Amazon SageMaker Canvas to build ML models and generate accurate predictions without writing a single line of code.
Get started with the tutorial »Dive deeper into SageMaker Canvas
Explore an in-depth look at SageMaker Canvas and its visual, no code ML capabilities.Use Amazon SageMaker Canvas to make your first ML Model
Learn how to use Amazon SageMaker Canvas to create an ML model to assess customer retention, based on an email campaign for new products and services. -
SageMaker Data Wrangler
-
Getting started with Amazon SageMaker Data Wrangler
Explore how set up SageMaker Data Wrangler and then provides a walkthrough using an existing example dataset.
Explore the guide »Prepare training data for machine learning with minimal code
Learn how to prepare data for ML using Amazon SageMaker Data Wrangler.
Get started with the tutorial »SageMaker Data Wrangler deep dive workshop
Learn how to apply appropriate analysis types on your dataset to detect anomalies and issues, use the derived results/insights to formulate remedial actions in the course of transformations on your dataset, and test the right choice and sequence of transformations using quick modeling options provided by SageMaker Data Wrangler. -
SageMaker Ground Truth/Ground Truth Plus
-
Getting Started with Amazon Groud Truth
Explore how to use the console to create a labeling job, assign a public or private workforce, and send the labeling job to your workforce. Learn how to monitor the progress of a labeling job.
Label Training Data for Machine Learning
Learn how to set up a labeling job in Amazon SageMaker Ground Truth to annotate training data for your ML model.
Getting started with Amazon Ground Truth Plus
Explore how to complete the necessary steps to start an Amazon SageMaker Ground Truth Plus project, review labels, and satisfy SageMaker Ground Truth Plus prerequisites.Get started with Amazon Ground Truth
Watch how to get started with labeling your data in minutes through the SageMaker Ground Truth console.
Amazon SageMaker Ground Truth Plus – create training datasets without code or in-house resources
Learn about Ground Truth Plus, a turn-key service that uses an expert workforce to deliver high-quality training datasets fast, and reduces costs by up to 40 percent.
-
SageMaker JumpStart
-
Get started with machine learning with SageMaker JumpStart
Explore SageMaker JumpStart solution templates that set up infrastructure for common use cases, and executable example notebooks for machine learning with SageMaker.
Explore the guide »Get Started with your machine learning project quickly using Amazon SageMaker JumpStart
Learn how to fast-track your ML project using pretrained models and prebuilt solutions offered by Amazon SageMaker JumpStart. You can then deploy the selected model through Amazon SageMaker Studio notebooks.
Get hands-on with Amazon SageMaker JumpStart with this Immersion Day workshop
Learn how the low-code ML capabilities found in Amazon SageMaker Data Wrangler, Autopilot and Jumpstart, make it easier to experiment faster and bring highly accurate models to production.
-
SageMaker Pipelines
-
Getting Started with Amazon SageMaker Pipelines
Learn how to create end-to-end workflows that manage and deploy SageMaker jobs. SageMaker Pipelines comes with SageMaker Python SDK integration, so you can build each step of your pipeline using a Python-based interface.
Explore the guide »Automate machine learning workflows
Learn how to create and automate end-to-end machine learning (ML) workflows using Amazon SageMaker Pipelines, Amazon SageMaker Model Registry, and Amazon SageMaker Clarify.
Get started with the tutorial »How to create fully automated ML workflows with Amazon SageMaker Pipelines
Learn about Amazon SageMaker Pipelines, the world’s first ML CI/CD service designed to be accessible for every developer and data scientist. SageMaker Pipelines brings CI/CD pipelines to ML, reducing the coding time required.
Watch the video » -
SageMaker Studio
-
Build and train a machine learning model locally
Learn how to build and train a ML model locally within your Amazon SageMaker Studio notebook.SageMaker Studio integration with EMR workshop
Learn how to utilize distributed processing at scale to prepare data and subsequently train machine learning models.
The third set of AI/ML AWS service pathways provide in-depth documentation, hands-on tutorials, and resources to get started with AWS Trainium, AWS Inferentia, and Amazon Titan.
-
AWS Trainium
-
AWS Inferentia
-
Amazon Titan
-
AWS Trainium
-
Scaling distributed training with AWS Trainium and Amazon EKS
Learn how you can benefit from the general availability of Amazon EC2 Trn1 instances powered by AWS Trainium—a purpose-built ML accelerator optimized to provide a high-performance, cost-effective, and massively scalable platform for training deep learning models in the cloud.
Overview of AWS Trainium
Learn about AWS Trainium, the second-generation machine learning (ML) accelerator that AWS purpose built for deep learning training of 100B+ parameter models. Each Amazon Elastic Compute Cloud (EC2) Trn1 instance deploys up to 16 AWS Trainium accelerators to deliver a high-performance, low-cost solution for deep learning (DL) training in the cloud.
Recommended Trainium Instances
Explore how AWS Trainium instances are designed to provide high performance and cost efficiency for deep learning model inference workloads.
-
AWS Inferentia
-
Overview of AWS Inferentia
Understand how accelerators are designed by AWS to deliver high performance at the lowest cost for your deep learning (DL) inference applications.
AWS Inferentia2 builds on AWS Inferentia1 by delivering 4x higher throughput and 10x lower latency
Understand what AWS Inferentia2 is optimized for - and explores how it was designed from the ground up to deliver higher performance while lowering the cost of LLMs and generative AI inference.
Machine learning inference using AWS Inferentia
Learn how to create an Amazon EKS cluster with nodes running Amazon EC2 Inf1 instances and (optionally) deploy a sample application. Amazon EC2 Inf1 instances are powered by AWS Inferentia chips, which are custom built by AWS to provide high performance and lowest cost inference in the cloud.
-
Amazon Titan
-
Overview of Amazon Titan
Explore how Amazon Titan FMs are pretrained on large datasets, making them powerful, general-purpose models. Learn how you can use them as is - or privately - to customize them with your own data for a particular task without annotating large volumes of data.
Explore
These reference architecture diagrams show examples of AWS AI and ML services in use.
Explore whitepapers to help you get started and learn best practices in choosing and using AI/ML services.
Explore vetted solutions and architectural guidance for common use cases for AI and ML services.
Additional resources
Supported foundation models include:
Anthropic Claude
Cohere Command & Embed
AI21 Labs Jurassic
Meta Llama
Mistral AI
Stable Diffusion XL
Amazon Titan
Using Bedrock, you can experiment with a variety of foundation models and privately customize them with your data.