NVIDIA paper enables cross-model KV cache transfer, skipping prefill 2.7-25x faster than recompute

blaizedsouza · x · 2026-09-09

A NVIDIA research paper introduces cross-model KV cache transfer: when swapping between models in a family (routing, cascading, mid-conversation switching), the receiver reuses the source model's KV cache and skips prefill entirely, with conversion running 2.7-25x faster than reprocessing the context.

Key findings:

Since cache hits are billed at roughly 10% of base input rate, making cache reuse portable across models could extend the biggest cost lever in LLM serving to routing and model cascades.

Original post →

More from Infra

Infra channel →