Amazon
Boost inference performance for Mixtral and Llama 2 models with new Amazon SageMaker containers
In January 2024, Amazon SageMaker launched a new version (0.26.0) of Large Model Inference (LMI) Deep Learning Containers (DLCs). This version offers support for new models (including Mixture of Experts), performance and usability improvements across inference backends, as well as new generation details for increased control and prediction explainability (such as reason for generation completion…
Amazon
AWS CloudTrail network activity events for VPC endpoints now generally available
AWS CloudTrail now offers network activity events for VPC endpoint logging, enabling comprehensive monitoring and recording of AWS API activity through VPC endpoints to enhance security visibility, detect unauthorized access, and prevent data exfiltration without requiring custom TLS traffic inspection solutions. Source
Amazon
Use language embeddings for zero-shot classification and semantic search with Amazon Bedrock
In this post, we explore what language embeddings are and how they can be used to enhance your application. We show how, by using the properties of embeddings, we can implement a real-time zero-shot classifier and can add powerful features such as semantic search. Source
Amazon
Build a dynamic, role-based AI agent using Amazon Bedrock inline agents
In this post, we explore how to build an application using Amazon Bedrock inline agents, demonstrating how a single AI assistant can adapt its capabilities dynamically based on user roles. Source