CORTEXA
← Browse
arxivcs.DCcs.AIcs.LG2026-06-30

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving

Jie Li, Tongyang Wang, Yong Chen

The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor. This survey classifies more than thirty KV-management systems and frameworks using four axes: locality, lifetime, ownership, and substrate. The axes reveal five architectural archetypes -- local-paged, disaggregated-pipeline, shared-store, memory-pool, and hybrid-tier. Once workload and hardware are fixed, ownership accounts for much of the remaining design variance among distributed systems. The survey also audits current evaluations and identifies seven missing KV-specific measurements, linking them to open problems in fault tolerance, isolation, tiered eviction, speculative decoding, MoE serving, and shared-cache semantics.

View free PDFSource page

Related papers

arxivcs.DCcs.AIcs.LG2026-07-11

Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices

Yangyijian Liu, Hongyi Ye, Mingyang Li, Wu-jun Li

Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory capacity, making offloading inference necessary to extend effective model capacity with CPU memory. Existing offloading systems, however, ty…

View free PDFSource page
arxivcs.ARcs.AIcs.CLcs.DCcs.LGcs.PF2026-07-21

BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators

Fabian Waschkowski, Prabod Rathnayaka, Lukas Wesemann

Apple's M5 generation introduces a redesigned GPU architecture in which every core carries a dedicated Neural Accelerator: on-die matrix units exposed through the Metal~4 tensor API. We show that BaseRT, our native Metal inference runtime for large language models on Apple Silico…

View free PDFSource page
arxivcs.LGcs.AIcs.DCcs.MAcs.NI2026-07-13

PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs

Jing Liu, Kun Yang, Yan Wang, Dingkang Yang, Xiaoshuai Hao, Wei Zhang, et al.

Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges. Within distributed network environments, Multimodal Large Language Models (MLLMs) serve as…

View free PDFSource page
arxivcs.DCcs.AIcs.LG2026-07-03

SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference

Huajun Bai, Weiwei Lv, Huichuan Zheng, Youyou Lu, Jiwu Shu

LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the result returns. This wait consumes 16-37% of wall time in our wor…

View free PDFSource page
arxivcs.LGcs.AIcs.DCcs.PF2026-07-16

An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism

Mobina Kashaniyan, Mehrdad Ashtiani, Amirhossein Ghassemi

Serverless computing provides automatic resource management and pay-per-use execution, but effective autoscaling remains challenging because of dynamic workloads, cold-start latency, and dependencies among functions. We present a dependency-aware autoscaling framework that integr…

View free PDFSource page