4 papers
AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding
Xu Yang, Jiapeng Zhang, Zhiwei Zuo +5
Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while controlling reconstruction err…
Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference
Xu Yang, Jiapeng Zhang, Zhangke +6
Sparse long-context inference requires efficient token retrieval in both prefill and decode. Existing methods often use different retrieval strategies for the two stages, preventin…
LIRAG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
Guo Chen, Junjie Huang, Huaijin Xie +2
Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models i…
MultiPath Memory Access: Breaking Host-GPU Bandwidth Bottlenecks in LLM Services
Lingfeng Tang, Daoping Zhang, Junjie Chen +6
Host-GPU data movement has become a latency-critical bottleneck in LLM serving, surfacing in common paths such as model-weight movement and KV cache offload/fetch. Today, each host…