arXiv AI By Meghana Maghyastha, Robert Underwood, Randal Burns, Bogdan Nicolae

PTStore (Prefix Tensor Store): Distributed Prefix Caching and Replication for High Throughput Inference Serving

Read the original on arXiv AI →

arXiv:2607. 22648v1 Announce Type: new Abstract: Inspired by the design of client caching in Content Delivery Networks (CDNs), PTStore distributes and replicates popular tensors that form reusable KV cache prefixes, which are the main technique used by state of art approaches to accelerate inferences.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 1

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving

arXiv:2605. 09735v2 Announce Type: replace-cross Abstract: Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular KV-cache behavior: request lengths differ, EOS events arrive asynchronously, and logical histories fragment over time.

By Zhiqing Zhong, Zhijing Ye, Jian Zhang, Weijian Zheng, Bolun Sun, Xiaodong Yu