{"total":89,"rows":[{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"area":"inference"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2405.04437","title":"vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention","created":"2024-05-07","cited_by_count":98,"area":"inference"},{"id":"2408.12757","title":"NanoFlow: Towards Optimal Large Language Model Serving Throughput","created":"2024-08-22","cited_by_count":90,"area":"inference"},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73,"area":"inference"},{"id":"2407.00023","title":"Preble: Efficient Distributed Prompt Scheduling for LLM Serving","created":"2024-05-08","cited_by_count":70,"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":"2504.15364","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","created":"2025-04-21","cited_by_count":51,"area":"inference"},{"id":"2403.01876","title":"D\\'ej\\`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving","created":"2024-03-04","cited_by_count":48,"area":"inference"},{"id":"2404.16283","title":"Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services","created":"2024-04-25","cited_by_count":45,"area":"inference"},{"id":"2402.01869","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","created":"2024-02-02","cited_by_count":33,"area":"inference"},{"id":"2408.05499","title":"LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale","created":"2024-08-10","cited_by_count":31,"area":"inference"},{"id":"2410.03065","title":"Compute Or Load KV Cache? Why Not Both?","created":"2024-10-04","cited_by_count":25,"area":"inference"},{"id":"2502.15470","title":"PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System","created":"2025-02-21","cited_by_count":20,"area":"inference"},{"id":"2502.07115","title":"Online Scheduling for LLM Inference with KV Cache Constraints","created":"2025-02-10","cited_by_count":19,"area":"inference"},{"id":"2504.19867","title":"semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage","created":"2025-04-28","cited_by_count":16,"area":"inference"},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2503.06433","title":"Seesaw: High-throughput LLM Inference via Model Re-sharding","created":"2025-03-09","cited_by_count":15,"area":"inference"},{"id":"2502.15524","title":"HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds","created":"2025-02-21","cited_by_count":14,"area":"inference"},{"id":"2504.14051","title":"CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction","created":"2025-04-18","cited_by_count":13,"area":"inference"},{"id":"2505.02922","title":"RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference","created":"2025-05-05","cited_by_count":13,"area":"inference"},{"id":"2406.01698","title":"Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models","created":"2024-06-03","cited_by_count":12,"area":"inference"},{"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":"2505.24196","title":"CLaSp: In-Context Layer Skip for Self-Speculative Decoding","created":"2025-05-30","cited_by_count":11,"area":"inference"},{"id":"2504.03775","title":"FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling","created":"2025-04-03","cited_by_count":10,"area":"inference"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2507.09019","title":"On Evaluating Performance of LLM Inference Serving Systems","created":"2025-07-11","cited_by_count":10,"area":"inference"},{"id":"2512.17910","title":"Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA","created":"2025-11-26","cited_by_count":8,"area":"inference"},{"id":"2508.06133","title":"LLM Serving Optimization with Variable Prefill and Decode Lengths","created":"2025-08-08","cited_by_count":7,"area":"inference"},{"id":"2509.00579","title":"KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache","created":"2025-08-30","cited_by_count":7,"area":"inference"},{"id":"2405.05329","title":"KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation","created":"2024-05-08","cited_by_count":6,"area":"inference"},{"id":"2504.09285","title":"DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM Serving","created":"2025-04-12","cited_by_count":6,"area":"inference"},{"id":"2505.23022","title":"Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference","created":"2025-05-29","cited_by_count":6,"area":"inference"},{"id":"2509.24626","title":"SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2602.22593","title":"FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving","created":"2026-02-26","cited_by_count":6,"area":"inference"},{"id":"2405.13019","title":"A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models","created":"2024-05-15","cited_by_count":5,"area":"inference"},{"id":"2410.14257","title":"Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving","created":"2024-10-18","cited_by_count":5,"area":"inference"},{"id":"2411.18424","title":"FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving","created":"2024-11-27","cited_by_count":5,"area":"inference"},{"id":"2511.21669","title":"DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving","created":"2025-11-26","cited_by_count":5,"area":"inference"},{"id":"2512.01953","title":"KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference","created":"2025-12-01","cited_by_count":4,"area":"inference"},{"id":"2601.11589","title":"LAPS: A Length-Aware-Prefill LLM Serving System","created":"2026-01-04","cited_by_count":4,"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":"2605.21312","title":"Frontier: Towards Comprehensive and Accurate LLM Inference Simulation","created":"2026-05-20","cited_by_count":4,"area":"inference"},{"id":"2509.17542","title":"Disaggregated Prefill and Decoding Inference System for Large Language Model Serving on Multi-Vendor GPUs","created":"2025-09-22","cited_by_count":3,"area":"inference"},{"id":"2605.00831","title":"GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving","created":"2026-03-26","cited_by_count":3,"area":"inference"},{"id":"2605.19049","title":"KVBuffer: IO-aware Serving for Linear Attention","created":"2026-05-18","cited_by_count":3,"area":"inference"},{"id":"2508.08457","title":"Architecting Long-Context LLM Acceleration with Packing-Prefetch Scheduler and Ultra-Large Capacity On-Chip Memories","created":"2025-08-11","cited_by_count":2,"area":"inference"},{"id":"2511.03092","title":"SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators","created":"2025-11-05","cited_by_count":2,"area":"inference"},{"id":"2512.24449","title":"PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression","created":"2025-12-30","cited_by_count":2,"area":"inference"},{"id":"2605.04595","title":"A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints","created":"2026-05-06","cited_by_count":2,"area":"inference"},{"id":"2606.06302","title":"Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving","created":"2026-06-04","cited_by_count":2,"area":"inference"},{"id":"2607.10987","title":"[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows","created":"2026-07-13","cited_by_count":2,"area":"inference"},{"id":"2502.13251","title":"Neural Attention Search","created":"2025-02-18","cited_by_count":1,"area":"inference"},{"id":"2507.02620","title":"FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference","created":"2025-07-03","cited_by_count":1,"area":"inference"},{"id":"2509.17357","title":"Cronus: Efficient LLM inference on Heterogeneous GPU Clusters via Partially Disaggregated Prefill","created":"2025-09-22","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":"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":"2603.10726","title":"PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems","created":"2026-03-11","cited_by_count":1,"area":"inference"},{"id":"2603.18016","title":"MineDraft: A Framework for Batch Parallel Speculative Decoding","created":"2026-02-24","cited_by_count":1,"area":"inference"},{"id":"2605.11999","title":"The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures","created":"2026-05-12","cited_by_count":1,"area":"inference"},{"id":"2608.06849","title":"Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry","created":"2026-08-07","cited_by_count":1,"area":"inference"},{"id":"2507.05043","title":"MoLink: Distributed and Efficient Serving Framework for Large Models","created":"2025-07-07","cited_by_count":0,"area":"inference"},{"id":"2510.05632","title":"Systematic Exploration of Multi-core Architectures for Efficient LLM Serving using WaferAI-SIM","created":"2025-10-07","cited_by_count":0,"area":"inference"},{"id":"2512.09427","title":"ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators","created":"2025-12-10","cited_by_count":0,"area":"inference"},{"id":"2604.17627","title":"SLO-Guard: Crash-Aware, Budget-Consistent Autotuning for SLO-Constrained LLM Serving","created":"2026-04-19","cited_by_count":0,"area":"inference"},{"id":"2604.26103","title":"AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving","created":"2026-04-28","cited_by_count":0,"area":"inference"},{"id":"2605.02189","title":"PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers","created":"2026-05-04","cited_by_count":0,"area":"inference"},{"id":"2605.08151","title":"SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference","created":"2026-05-04","cited_by_count":0,"area":"inference"},{"id":"2605.19593","title":"Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption","created":"2026-05-19","cited_by_count":0,"area":"inference"},{"id":"2606.15555","title":"Service-Induced Congestion in Memory-Constrained LLM Serving","created":"2026-06-14","cited_by_count":0,"area":"inference"},{"id":"2606.20577","title":"Human-Less LLM Serving: Quantifying the Human Tax on Throughput","created":"2026-05-03","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":"2607.08930","title":"BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving","created":"2026-07-09","cited_by_count":0,"area":"inference"},{"id":"2607.28848","title":"DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs","created":"2026-07-30","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":"2608.15943","title":"KV-Pipe: On the Relation Between KV Sharing and Pipeline Parallel Efficiency in LLMs","created":"2026-08-16","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":"2608.16477","title":"Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN","created":"2026-08-17","cited_by_count":0,"area":"inference"},{"id":"2609.00857","title":"LLM Inference on IMC-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism","created":"2026-09-01","cited_by_count":0,"area":"inference"},{"id":"2609.07966","title":"MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.11392","title":"PATTON: Enabling Commodity PIM for Production LLM Serving","created":"2026-09-10","cited_by_count":0,"area":"inference"},{"id":"2609.37062","title":"vSkipper: Translating Dynamic Layer Skipping into LLM Serving Gains","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.14688","title":"Accelerating Cross-Model LLM Inference via Attention Map Reuse","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"id":"2610.15899","title":"Lightweight Scheduling Policies for Continuously Batched LLM Serving Across GPU Architectures","created":"2026-10-11","cited_by_count":0,"area":"inference"}],"next_cursor":null}