[{"data":1,"prerenderedAt":24},["ShallowReactive",2],{"reinvent2023-CON303":3},{"id":4,"title":5,"categories":6,"contributors":10,"cover":11,"description":12,"extension":13,"meta":14,"path":15,"services":16,"sessionId":19,"skillLevel":20,"stem":21,"type":22,"__hash__":23},"reinvent2023\u002Freinvent2023\u002FCON303.json","Deploy LLM models efficiently and at scale with serverless containers",[7,8,9],"Cost Optimization","Business Intelligence","Serverless Compute",null,"\u002Fassets\u002Fimages\u002Freinvent2023\u002FCON303.jpg","More and more, organizations are looking to start deploying LLM models to solve for a variety of business use cases. In this session, review the various infrastructure options and integrations that can help you deploy LLM models using Amazon ECS: CPU inference, Amazon ECS with AWS Fargate, accelerated inference with GPU and Inf1, Amazon ECS on Amazon EC2, and associated storage and networking options.","json",{},"\u002Freinvent2023\u002FCON303",[17,18],"fargate","ecs","CON303","300","reinvent2023\u002FCON303","Breakout Session","rmQamxmarGnDHqFDNP2Lfh22OYxe43TyB937fDhb3I4",1792665336172]