{"total":98,"rows":[{"id":"2501.01005","title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving","created":"2025-01-02","cited_by_count":258,"area":"inference"},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91,"area":"inference"},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86,"area":"inference"},{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2406.17565","title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool","created":"2024-06-25","cited_by_count":68,"area":"inference"},{"id":"2410.18038","title":"POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","created":"2024-10-23","cited_by_count":47,"area":null},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"area":null},{"id":"2504.02441","title":"Cognitive Memory in Large Language Models","created":"2025-04-03","cited_by_count":29,"area":null},{"id":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2505.04021","title":"Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning","created":"2025-05-06","cited_by_count":24,"area":"inference"},{"id":"2603.18897","title":"Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving","created":"2026-03-19","cited_by_count":20,"area":"agents"},{"id":"2504.08784","title":"SLOs-Serve: Optimized Serving of Multi-SLO LLMs","created":"2025-04-05","cited_by_count":19,"area":null},{"id":"2504.19720","title":"Taming the Titans: A Survey of Efficient LLM Inference Serving","created":"2025-04-28","cited_by_count":16,"area":"inference"},{"id":"2601.17768","title":"LLM-42: Enabling Determinism in LLM Inference with Verified Speculation","created":"2026-01-25","cited_by_count":16,"area":null},{"id":"2407.15309","title":"vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving","created":"2024-07-22","cited_by_count":15,"area":"inference"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2412.18169","title":"KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving","created":"2024-12-24","cited_by_count":11,"area":"inference"},{"id":"2603.16104","title":"Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective","created":"2026-03-17","cited_by_count":11,"area":"agents"},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2602.06502","title":"DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving","created":"2026-02-06","cited_by_count":8,"area":"inference"},{"id":"2503.22562","title":"Niyama : Breaking the Silos of LLM Inference Serving","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2606.20537","title":"Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving","created":"2026-06-18","cited_by_count":7,"area":"inference"},{"id":"2505.24584","title":"AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up","created":"2025-05-30","cited_by_count":6,"area":"agents"},{"id":"2502.01677","title":"Position: AI Scaling: From Up to Down and Out","created":"2025-02-02","cited_by_count":5,"area":null},{"id":"2506.15155","title":"eLLM: Elastic Memory Management Framework for Efficient LLM Serving","created":"2025-06-18","cited_by_count":5,"area":"inference"},{"id":"2512.09472","title":"WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving","created":"2025-12-10","cited_by_count":5,"area":"inference"},{"id":"2604.06036","title":"CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference","created":"2026-04-07","cited_by_count":5,"area":"mllm"},{"id":"2503.04253","title":"ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput","created":"2025-03-06","cited_by_count":4,"area":"inference"},{"id":"2504.19516","title":"Boosting LLM Serving through Spatial-Temporal GPU Resource Sharing","created":"2025-04-28","cited_by_count":4,"area":"inference"},{"id":"2507.03153","title":"HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2510.02613","title":"ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models","created":"2025-10-02","cited_by_count":4,"area":"moe"},{"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":"2605.20868","title":"Runtime-Certified Bounded-Error Quantized Attention","created":"2026-05-20","cited_by_count":4,"area":"inference"},{"id":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"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":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2509.06261","title":"FineServe: Precision-Aware KV Slab and Two-Level Scheduling for Heterogeneous Precision LLM Serving","created":"2025-09-08","cited_by_count":3,"area":"inference"},{"id":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2510.14686","title":"xLLM Technical Report","created":"2025-10-16","cited_by_count":3,"area":"inference"},{"id":"2604.12171","title":"PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving","created":"2026-04-14","cited_by_count":3,"area":"inference"},{"id":"2508.18736","title":"Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2509.04827","title":"VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing","created":"2025-09-05","cited_by_count":2,"area":"inference"},{"id":"2512.15705","title":"Dynamic Rebatching for Efficient Early-Exit Inference with DREX","created":"2025-12-17","cited_by_count":2,"area":"inference"},{"id":"2601.06562","title":"Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming","created":"2026-01-10","cited_by_count":2,"area":null},{"id":"2601.15335","title":"ToolCaching: Towards Efficient Caching for LLM Tool-calling","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2603.13430","title":"Dynamic Sparse Attention: Access Patterns and Architecture","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2604.06664","title":"Foundry: Template-Based CUDA Graph Context Materialization for Fast LLM Serving Cold Start","created":"2026-04-08","cited_by_count":2,"area":"inference"},{"id":"2604.18529","title":"HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing","created":"2026-04-20","cited_by_count":2,"area":"inference"},{"id":"2606.18741","title":"ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving","created":"2026-06-17","cited_by_count":2,"area":"inference"},{"id":"2607.08565","title":"SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling","created":"2026-07-09","cited_by_count":2,"area":"agents"},{"id":"2607.28150","title":"SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer","created":"2026-07-30","cited_by_count":2,"area":"inference"},{"id":"2609.07883","title":"Deadline-Aware Adaptive Prefill Chunking for Efficient Large Language Model Serving","created":"2026-09-07","cited_by_count":2,"area":"inference"},{"id":"2410.15651","title":"Understanding and Alleviating Memory Consumption in RLHF for LLMs","created":"2024-10-21","cited_by_count":1,"area":"alignment"},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2506.07311","title":"Paged Attention Meets FlexAttention: Unlocking Long-Context Efficiency in Deployed Inference","created":"2025-06-08","cited_by_count":1,"area":"inference"},{"id":"2601.03067","title":"Joint Encoding of KV-Cache Blocks for Scalable LLM Serving","created":"2026-01-06","cited_by_count":1,"area":"inference"},{"id":"2601.13631","title":"ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management","created":"2026-01-20","cited_by_count":1,"area":"inference"},{"id":"2602.15379","title":"FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.05692","title":"Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.07609","title":"Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.16682","title":"KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving","created":"2026-04-17","cited_by_count":1,"area":"agents"},{"id":"2605.06105","title":"Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.22850","title":"ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse","created":"2026-05-16","cited_by_count":1,"area":"inference"},{"id":"2606.02430","title":"Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2608.13263","title":"vToken: Token-Level Virtualization for Reclaimable KV Caches","created":"2026-08-13","cited_by_count":1,"area":"inference"},{"id":"2608.14498","title":"Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training","created":"2026-08-14","cited_by_count":1,"area":"mllm"},{"id":"2609.18675","title":"HBFlex: A Flexible Memory System for Bridging Fine-Grained LLM States and Coarse-Grained HBF Parallel Execution","created":"2026-09-16","cited_by_count":1,"area":"inference"},{"id":"2503.13773","title":"Mitigating KV Cache Competition to Enhance User Experience in LLM Inference","created":"2025-03-17","cited_by_count":0,"area":"inference"},{"id":"2511.00101","title":"Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.12031","title":"Striking the Right Balance between Compute and Copy: Improving LLM Inferencing Under Speculative Decoding","created":"2025-11-15","cited_by_count":0,"area":"inference"},{"id":"2605.06046","title":"Requests of a Feather Must Flock Together: Batch Size vs. Prefix Homogeneity in LLM Inference","created":"2026-05-07","cited_by_count":0,"area":"inference"},{"id":"2605.22416","title":"Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference","created":"2026-05-21","cited_by_count":0,"area":"ssm"},{"id":"2606.11916","title":"Characterizing Software Aging in GPU-Based LLM Serving Systems","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.21848","title":"Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers","created":"2026-06-20","cited_by_count":0,"area":"inference"},{"id":"2606.25353","title":"Cache-Resident LLM Inference in GB-Scale Last-Level Caches","created":"2026-06-24","cited_by_count":0,"area":"inference"},{"id":"2606.26666","title":"PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs","created":"2026-06-25","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":"2608.16336","title":"Beyond Binary Priorities: Multi-Tier SLA Scheduling for Large Language Model Serving","created":"2026-08-17","cited_by_count":0,"area":"inference"},{"id":"2608.20397","title":"Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2608.23658","title":"Elastic KV Cache for LLM Serving:A Working Reclamation Mechanism, and Why Chunked Prefill Already Closes the Gap","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2608.24650","title":"Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2608.29255","title":"A-MADiff: Attention-Guided Multi-Agent DRL with Diffusion Policies for Memory-Aware Task Orchestration in Mobile AIGC Networks","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.02029","title":"HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03494","title":"GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.13537","title":"Dynamic HBM Repartitioning for Multi-Turn MoE Serving","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.14507","title":"Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.19203","title":"Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"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":"2609.23816","title":"SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference","created":"2026-09-20","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":"2609.34380","title":"DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.34653","title":"OmniTide: Co-Designing Algorithms and Systems for Efficient On-Device Omni-LLM Streaming","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.00437","title":"JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.06917","title":"FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving","created":"2026-10-02","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"},{"id":"2610.18451","title":"FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}