As DeepSeek-R1 has become a trending topic due to its reasoning ability, we have heard questions on how to deploy the model or its distilled models on AWS.

This topic is extended into how startups can deploy open source LLMs on AWS in general. This 1.5 hour session is exactly about that. Let's dive deeper into DeepSeek-R1 models, the possible ways to deploy them on AWS, and how to get started with those models on AWS including potential experimentation credits.

Learn about deploying DeepSeek-R1 distilled models in a cost-optimized way with Scale Down to Zero on Amazon SageMaker and with Graviton4 CPU on EC2.

Join this session to learn all this together.