{"total":62,"rows":[{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2512.03416","title":"TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity","created":"2025-12-03","cited_by_count":12,"area":"inference"},{"id":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2606.16824","title":"CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents","created":"2026-06-15","cited_by_count":10,"area":"inference"},{"id":"2602.23036","title":"LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure","created":"2026-02-26","cited_by_count":9,"area":"inference"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"id":"2605.13734","title":"KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving","created":"2026-05-13","cited_by_count":7,"area":"inference"},{"id":"2511.00868","title":"FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management","created":"2025-11-02","cited_by_count":5,"area":"inference"},{"id":"2601.12967","title":"Sutradhara: An Intelligent Orchestrator-Engine Co-design for Tool-based Agentic Inference","created":"2026-01-19","cited_by_count":5,"area":"inference"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2602.12029","title":"PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving","created":"2026-02-12","cited_by_count":4,"area":"inference"},{"id":"2604.26837","title":"Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving","created":"2026-04-29","cited_by_count":4,"area":"inference"},{"id":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2511.12752","title":"Whose Narrative is it Anyway? A KV Cache Manipulation Attack","created":"2025-11-16","cited_by_count":3,"area":"inference"},{"id":"2605.07719","title":"An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"id":"2511.14510","title":"LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference","created":"2025-11-18","cited_by_count":2,"area":"inference"},{"id":"2604.26557","title":"DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference","created":"2026-04-29","cited_by_count":2,"area":"inference"},{"id":"2605.18856","title":"SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference","created":"2026-05-13","cited_by_count":2,"area":"inference"},{"id":"2606.16135","title":"SwiftCache: Efficient LLM Serving for Multi-turn Conversations with Heterogeneous KV Cache Sharing","created":"2026-06-15","cited_by_count":2,"area":"inference"},{"id":"2606.31519","title":"RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference","created":"2026-06-30","cited_by_count":2,"area":"inference"},{"id":"2601.19910","title":"Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading","created":"2025-12-16","cited_by_count":1,"area":"inference"},{"id":"2603.04716","title":"SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference","created":"2026-03-05","cited_by_count":1,"area":"inference"},{"id":"2603.08739","title":"Adaptive Multi-Objective Tiered Storage Configuration for KV Cache in LLM Service","created":"2026-02-25","cited_by_count":1,"area":"inference"},{"id":"2604.00368","title":"TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving","created":"2026-04-01","cited_by_count":1,"area":"inference"},{"id":"2604.26968","title":"Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference","created":"2026-04-19","cited_by_count":1,"area":"inference"},{"id":"2605.22850","title":"ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse","created":"2026-05-16","cited_by_count":1,"area":"inference"},{"id":"2606.01502","title":"Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics","created":"2026-05-31","cited_by_count":1,"area":"inference"},{"id":"2606.03910","title":"NetKV: Network-Aware Decode Instance Selection for Disaggregated LLM Inference","created":"2026-06-02","cited_by_count":1,"area":"inference"},{"id":"2606.17059","title":"Towards Distributed Inference of LLMs on a P2P Network","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2607.18141","title":"A CXL Memory Rack for Multi-Turn LLM Serving","created":"2026-07-20","cited_by_count":1,"area":"inference"},{"id":"2607.22648","title":"PTStore (Prefix Tensor Store): Distributed Prefix Caching and Replication for High Throughput Inference Serving","created":"2026-06-25","cited_by_count":1,"area":"inference"},{"id":"2607.27090","title":"InferScale: GPU-Native KV Injection for Personalized LLM Serving","created":"2026-07-29","cited_by_count":1,"area":"inference"},{"id":"2604.09562","title":"StreamServe: Adaptive Speculative Flows for Low-Latency Disaggregated LLM Serving","created":"2026-02-11","cited_by_count":0,"area":"inference"},{"id":"2605.09735","title":"KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving","created":"2026-05-10","cited_by_count":0,"area":"inference"},{"id":"2606.14779","title":"Unified KV Pooling to Accelerate Long-Context LLM Serving","created":"2026-06-10","cited_by_count":0,"area":"inference"},{"id":"2606.21633","title":"HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval","created":"2026-06-19","cited_by_count":0,"area":"inference"},{"id":"2606.31093","title":"Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.00151","title":"SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.02525","title":"PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving","created":"2026-05-10","cited_by_count":0,"area":"inference"},{"id":"2607.02574","title":"From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.26633","title":"NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement","created":"2026-07-29","cited_by_count":0,"area":"inference"},{"id":"2608.01891","title":"Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling","created":"2026-08-03","cited_by_count":0,"area":"inference"},{"id":"2608.06007","title":"TensorCast: The Missing Tensor Management Layer in Large Language Model Infrastructure","created":"2026-08-06","cited_by_count":0,"area":"inference"},{"id":"2608.13573","title":"A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing","created":"2026-07-03","cited_by_count":0,"area":"inference"},{"id":"2608.17826","title":"Bounded-State Restoration: Decoupling Local Restore Capacity from External LLM State","created":"2026-08-18","cited_by_count":0,"area":"inference"},{"id":"2608.23834","title":"Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.16215","title":"Where Should the KV Cache Live? Placement Policies Across GPU, CPU, and SSD for Long-Lived Sessions","created":"2026-09-14","cited_by_count":0,"area":"inference"},{"id":"2609.19657","title":"PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving","created":"2026-09-17","cited_by_count":0,"area":"inference"},{"id":"2609.25451","title":"Fast Recovery for LLM Serving via Decoupled Device Memory Lifetime in Dynamo","created":"2026-09-21","cited_by_count":0,"area":"inference"},{"id":"2609.27746","title":"The KV Cache Working Set: Online Capacity Planning for LLM Inference Systems","created":"2026-09-23","cited_by_count":0,"area":"inference"},{"id":"2609.30854","title":"The KV Cache Is the New Memory Wall","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.31415","title":"Evaluating the accuracy of KV cache reuse techniques","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.33536","title":"Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.33759","title":"Positions Are Not Facts: The Mismatch Between KV Caches and Memory","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.34727","title":"Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.35065","title":"TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.39131","title":"Characterizing High Bandwidth Flash for LLM Serving","created":"2026-09-30","cited_by_count":0,"area":"inference"},{"id":"2610.13060","title":"KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse","created":"2026-10-09","cited_by_count":0,"area":"inference"},{"id":"2610.17970","title":"AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.18143","title":"RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}