gcp Google Cloud release notes ·

Bigtable integrates with LMCache for LLM KV caching

aigcppreviewengineer
feature

Google Cloud Bigtable can now serve as a remote storage backend for LMCache. This allows multiple AI serving instances to share and reuse precomputed attention tensors for LLM key-value caches, reducing compute overhead and improving time-to-first-token for repeated prompts. The feature is currently in Preview and intended for users running AI serving workloads.

Features (1)
  • Bigtable

    You can use Bigtable as a remote storage backend for LMCache . By storing the large language model (LLM) key-value (KV) cache externally in Bigtable, multiple AI serving instances can share and reuse precomputed attention tensors. This reduces compute overhead and significantly improves time-to-first-token (TTFT) for repeated prompts and shared documents. This feature is in Preview .

Read the original announcement →

https://docs.cloud.google.com/release-notes#July_30_2026

Related releases