Category: Compute

Although batch inference offers numerous benefits, it’s limited to 10 batch inference jobs submitted per model per Region. To address this consideration and enhance your use of batch inference, we’ve developed a scalable solution using AWS Lambda and HAQM DynamoDB. This post guides you through implementing a queue management system that automatically monitors available job slots and submits new jobs as slots become available.

In this post, we explore a sample solution that you can use to deploy an image editing application by using AWS serverless services and generative AI services. We use HAQM Bedrock and an HAQM Titan FM that allow you to edit images by using prompts.

In this post, we show how to create a multimodal chat assistant on HAQM Web Services (AWS) using HAQM Bedrock models, where users can submit images and questions, and text responses will be sourced from a closed set of proprietary documents.

In this post, we show you the Employee Productivity GenAI Assistant Example, a solution built on AWS technologies like HAQM Bedrock, to automate writing tasks and enhance employee productivity.

In this post, we present to you an in-depth guide to starting a continual pre-training job using PyTorch Fully Sharded Data Parallel (FSDP) for Mistral AI’s Mathstral model with SageMaker HyperPod.

In this post, we show you how Zeta Global, a data-driven marketing technology company, has built an efficient MLOps platform to streamline the end-to-end ML workflow, from data ingestion to model deployment, while optimizing resource utilization and cost efficiency.

This post is designed for Kubernetes cluster administrators and ML scientists, providing an overview of the key features that SageMaker HyperPod introduces to facilitate large-scale model training on an EKS cluster.

In this post, we discuss the core capabilities of HAQM Elastic Compute Cloud (HAQM EC2) P5e instances and the use cases they’re well-suited for. We walk you through an example of how to get started with these instances and carry out inference deployment of Meta Llama 3.1 70B and 405B models on them.

This post explores how Accenture used the customization capabilities of Knowledge Bases for HAQM Bedrock to incorporate their data processing workflow and custom logic to create a custom chunking mechanism that enhances the performance of Retrieval Augmented Generation (RAG) and unlock the potential of your PDF data.

In today’s rapidly evolving landscape of artificial intelligence (AI), training large language models (LLMs) poses significant challenges. These models often require enormous computational resources and sophisticated infrastructure to handle the vast amounts of data and complex algorithms involved. Without a structured framework, the process can become prohibitively time-consuming, costly, and complex. Enterprises struggle with managing […]