{"total":88,"rows":[{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2502.14051","title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression","created":"2025-02-19","cited_by_count":41,"area":"inference"},{"id":"2502.12216","title":"Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs","created":"2025-02-17","cited_by_count":24,"area":"inference"},{"id":"2505.07203","title":"PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications","created":"2025-05-12","cited_by_count":21,"area":"inference"},{"id":"2603.18567","title":"SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding","created":"2026-03-19","cited_by_count":16,"area":"inference"},{"id":"2601.11580","title":"Speculative Decoding: Performance or Illusion?","created":"2025-12-31","cited_by_count":15,"area":"inference"},{"id":"2603.03251","title":"Speculative Speculative Decoding","created":"2026-03-03","cited_by_count":15,"area":"inference"},{"id":"2502.01068","title":"FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration","created":"2025-02-03","cited_by_count":14,"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":"2507.06608","title":"Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving","created":"2025-07-09","cited_by_count":13,"area":"inference"},{"id":"2501.14808","title":"HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location","created":"2025-01-15","cited_by_count":10,"area":"inference"},{"id":"2604.03143","title":"TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing","created":"2026-04-03","cited_by_count":8,"area":"inference"},{"id":"2502.04077","title":"AttentionPredictor: Temporal Patterns Matter for KV Cache Compression","created":"2025-02-06","cited_by_count":7,"area":"inference"},{"id":"2505.22913","title":"Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference","created":"2025-05-28","cited_by_count":7,"area":"inference"},{"id":"2506.02572","title":"HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference","created":"2025-06-03","cited_by_count":7,"area":"inference"},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2508.01002","title":"Optimal Scheduling Algorithms for LLM Inference: Theory and Practice","created":"2025-08-01","cited_by_count":6,"area":"inference"},{"id":"2508.17219","title":"TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving","created":"2025-08-24","cited_by_count":5,"area":"inference"},{"id":"2511.22880","title":"Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems","created":"2025-11-28","cited_by_count":5,"area":"inference"},{"id":"2604.10539","title":"IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs","created":"2026-04-12","cited_by_count":5,"area":"inference"},{"id":"2605.18071","title":"KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference","created":"2026-05-18","cited_by_count":5,"area":"inference"},{"id":"2504.04104","title":"SpecPipe: Accelerating Pipeline Parallelism-based LLM Inference with Speculative Decoding","created":"2025-04-05","cited_by_count":4,"area":"inference"},{"id":"2508.09001","title":"Retrospective Sparse Attention for Efficient Long-Context Generation","created":"2025-08-12","cited_by_count":4,"area":"inference"},{"id":"2510.13602","title":"NOSA: Native and Offloadable Sparse Attention","created":"2025-10-15","cited_by_count":4,"area":"inference"},{"id":"2602.02108","title":"Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts","created":"2026-02-02","cited_by_count":4,"area":"inference"},{"id":"2602.21224","title":"Make Every Draft Count: Hidden State based Speculative Decoding","created":"2026-02-02","cited_by_count":4,"area":"inference"},{"id":"2605.13111","title":"Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation","created":"2026-05-13","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":"2605.21312","title":"Frontier: Towards Comprehensive and Accurate LLM Inference Simulation","created":"2026-05-20","cited_by_count":4,"area":"inference"},{"id":"2605.30571","title":"Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM Decode","created":"2026-05-28","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":"2509.24328","title":"Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding","created":"2025-09-29","cited_by_count":3,"area":"inference"},{"id":"2601.13684","title":"HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference","created":"2026-01-20","cited_by_count":3,"area":"inference"},{"id":"2602.00269","title":"VoxServe: Streaming-Centric Serving System for Speech Language Models","created":"2026-01-30","cited_by_count":3,"area":"inference"},{"id":"2603.05931","title":"A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA","created":"2026-03-06","cited_by_count":3,"area":"inference"},{"id":"2607.22634","title":"PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding","created":"2026-06-20","cited_by_count":3,"area":"inference"},{"id":"2607.28699","title":"WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization","created":"2026-07-30","cited_by_count":3,"area":"inference"},{"id":"2608.01651","title":"Bole: Efficient Tree Speculation for Hybrid-Attention Language Models","created":"2026-08-03","cited_by_count":3,"area":"inference"},{"id":"2504.09590","title":"Efficient LLM Serving on Hybrid Real-time and Best-effort Requests","created":"2025-04-13","cited_by_count":2,"area":"inference"},{"id":"2508.03611","title":"Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling","created":"2025-08-05","cited_by_count":2,"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":"2511.18868","title":"KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits","created":"2025-11-24","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":"2605.12110","title":"AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference","created":"2026-05-12","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":"2606.04446","title":"D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models","created":"2026-06-03","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":"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":"2609.17184","title":"LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers","created":"2026-09-15","cited_by_count":2,"area":"inference"},{"id":"2502.13251","title":"Neural Attention Search","created":"2025-02-18","cited_by_count":1,"area":"inference"},{"id":"2507.08045","title":"Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing","created":"2025-07-10","cited_by_count":1,"area":"inference"},{"id":"2510.27641","title":"SpecAttn: Speculating Sparse Attention","created":"2025-10-31","cited_by_count":1,"area":"inference"},{"id":"2512.19179","title":"CascadeInfer: Length-Aware Scheduling of LLM Serving with Low Latency and Load Balancing","created":"2025-12-22","cited_by_count":1,"area":"inference"},{"id":"2602.20732","title":"CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference","created":"2026-02-24","cited_by_count":1,"area":"inference"},{"id":"2603.27138","title":"ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference","created":"2026-03-28","cited_by_count":1,"area":"inference"},{"id":"2604.00235","title":"MAC-Attention: a Match-Amend-Complete Scheme for Fast and Accurate Attention Computation","created":"2026-03-31","cited_by_count":1,"area":"inference"},{"id":"2605.01910","title":"Stochastic Sparse Attention for Memory-Bound Inference","created":"2026-05-03","cited_by_count":1,"area":"inference"},{"id":"2605.17633","title":"SparseSAM: Structured Sparsification of Activations in Segment Anything Models","created":"2026-05-17","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":"2607.00760","title":"MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression","created":"2026-07-01","cited_by_count":1,"area":"inference"},{"id":"2608.02947","title":"ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference","created":"2026-08-03","cited_by_count":1,"area":"inference"},{"id":"2608.15533","title":"DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding","created":"2026-08-16","cited_by_count":1,"area":"inference"},{"id":"2609.17943","title":"ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference","created":"2026-09-16","cited_by_count":1,"area":"inference"},{"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":"2509.23384","title":"A Predictive and Synergistic Two-Layer Scheduling Framework for LLM Serving","created":"2025-09-27","cited_by_count":0,"area":"inference"},{"id":"2603.04797","title":"Hardware-Software Co-design for 3D-DRAM-based LLM Serving Accelerator","created":"2026-03-05","cited_by_count":0,"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":"2605.00616","title":"LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling","created":"2026-05-01","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":"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":"2607.02640","title":"Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving","created":"2026-07-02","cited_by_count":0,"area":"inference"},{"id":"2607.20475","title":"SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification","created":"2026-05-24","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":"2608.15584","title":"GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix","created":"2026-08-16","cited_by_count":0,"area":"inference"},{"id":"2609.23900","title":"LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.26796","title":"Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs","created":"2026-09-22","cited_by_count":0,"area":"inference"},{"id":"2609.33410","title":"FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward","created":"2026-09-27","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":"2609.34388","title":"Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier","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":"2609.37626","title":"SPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.04313","title":"MOIRA: Mass-Oriented Indexing with Ragged Attention for Long-Context Decoding","created":"2026-10-03","cited_by_count":0,"area":"inference"},{"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":"2610.09051","title":"A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"id":"2610.14448","title":"KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization","created":"2026-10-10","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}