AWS & NVIDIA Webinar 4: Optimizing Inference and GenAI Deployment on Amazon SageMaker

Events
AWS & NVIDIA Webinar 4: Optimizing Inference and GenAI Deployment on Amazon SageMaker

일:

시간:

유형:

온라인

발표자:

Vivek Gangasani | Sr. ML Specialist SA, AWS, Kareem Abdol Hamid | Sr. SSA HPC, Amazon Web Services , Curt Lockhart | Sr. AI Solution Architect, NVIDIA

언어:

English

레벨:

200 - 중급, 300 - 고급

이벤트 세부 정보

일

시간

유형

온라인

발표자

Explore the best practices for Amazon SageMaker Inference and model deployment. This session will cover NVIDIA Inference Microservices (NIMs), inference optimization techniques, and demonstrate how to leverage the latest LLM models through Amazon Bedrock Marketplace, including Amazon Nova in a serverless fashion.

This advanced session is ideal for Startups focused on model deployment, inference optimization, and scaling their AI services.

Check out the other sessions of this Enablement Series here.

Agenda

5:30 PM UTC

Introduction to SageMaker Inference

6:00 PM UTC

NVIDIA Inference Microservices (NIMs)

6:20 PM UTC

Inference Optimization Best Practices

6:40 PM UTC

Ask an Expert Q&A Session