cs.LGNov 16, 2026

KVUse: Reusable-KV User Memory for Efficient LLM Recommenders

Authors: Xin Guo, Qiang Zhang, Xiang Zhou, Arushi Rai, Siyu Lin, Yifan Wu, Xiang Shen, Lei Huang, 

Organizations: Meta Recommendation Systems (MRS)

Abstract

Memory-augmented recommenders built on large language models (LLMs) maintain a natural-language profile of each user. These profiles are updated by a user profile update path that revises the profile as new interactions arrive and are consumed by downstream task paths like ranking. Because these user profiles are stored as text in the user memory, every ranking LLM call that consumes them must splice them in the prompt and calculate the KV cache of them during the prefill phase. Given these ranking LLM calls are prefill heavy (long prompt but short decoded output) and repeatedly called, these repeated prefill of user profile text dominates the serving. Prefix caching cannot remove it, because these user profiles are preceded by different text in different calls. We present KVUse, which stores the user profiles as reusable key-value (KV) caches instead of text. KVUse trains lightweight LoRA writers by self-distillation, so that the user profile update call produces the reusable KV of the user profile while decoding it, and the LLM can read these reusable KV at new positions and behind new context without recomputation. KVUse also has a customized KV scheduler that uploads the stored reusable KV of the next batch while the current batch is computed, hiding the KV transfer from host memory behind GPU computation. On four InstructRec datasets with Llama-3.1-8B-Instruct, KVUse shows no statistically significant difference in ranking quality from full prefill over continuous memory update rounds. Under saturated load, KVUse raises the throughput of the downstream scoring path by 4.0x-4.5x and of the profile update path by 1.4x-1.9x.

Figures & tables

Explore similar work

CardsList
  1. InferScale: GPU-Native KV Injection for Personalized LLM Serving

    Jul 29, 2026Peter Li, Prashant PandeyLLM ServingMemory-Augmented Language Models

  2. KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

    Sep 9, 2026Xi Shi, Mengxin Zheng, Qian LouKV CachingLLM Inference Acceleration

  3. KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse

    Oct 9, 2026Taiga Ikeda, Daisuke Miyashita, Jun DeguchiKV-Cache ReuseKV-Cache Management