API
< Back to all clusters
[TECHNOLOGY] · United States · 2 sources

started · updated

Amazon ElastiCache for Valkey introduces new caching capabilities

Amazon has expanded its ElastiCache for Valkey service with two major updates. First, the service now supports distributed KV caching designed for self-hosted large language model (LLM) inference. This feature aims to reduce inference costs by up to 40% and improve time to first token (TTFT) by up to 80% by allowing servers to share KV state across sessions and routing shifts.

Additionally, Amazon announced DynamoDB caching for ElastiCache Serverless for Valkey. This functionality allows DynamoDB reads to be routed through an ElastiCache Serverless for Valkey cache to improve performance. The distributed KV caching feature is currently available in 13 AWS Regions across the US, Europe, and Asia Pacific.

Entities

AWS · Amazon · Amazon ElastiCache · DynamoDB · Valkey