ElastiCache distributed KV caching
Fully managed distributed KV caching for self-hosted LLMs is generally available, cutting inference costs by up to 40% and TTFT by up to 80%.
The Deploy Log | Products | Free, no signup
7 updates to Amazon ElastiCache from Amazon Web Services in The Deploy Log: each row Amazon Web Services published whose subject opens with Amazon ElastiCache or ElastiCache or names a feature in it. By publisher's dates alone: from to , a new one every 8 days on the median, the longest wait was 18 days, and 4 updates in the last 30 days. The newest is ElastiCache distributed KV caching. Each links the publisher's own page.
| Update | Date | Days after the one before |
|---|---|---|
| ElastiCache distributed KV caching | 8 | |
| ElastiCache Serverless vector search | 14 | |
| ElastiCache data tiering | 0 | |
| ElastiCache for Valkey durability change | 7 | |
| ElastiCache Serverless for Valkey | 18 | |
| ElastiCache for Valkey OpenTelemetry | 3 | |
| ElastiCache Serverless for Valkey |
Fully managed distributed KV caching for self-hosted LLMs is generally available, cutting inference costs by up to 40% and TTFT by up to 80%.
Amazon ElastiCache Serverless now supports vector, full-text, and hybrid searches plus aggregations.
Data tiering is now available on R8gd and R7gd nodes in Europe (Spain) and Asia Pacific (Hyderabad).
Amazon ElastiCache for Valkey now supports changing durability on existing clusters.
Amazon ElastiCache Serverless for Valkey now supports online migration with zero downtime.
Amazon ElastiCache for Valkey now supports OpenTelemetry metrics and detailed monitoring.
Amazon ElastiCache Serverless for Valkey now supports public endpoints.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.