{"total":240,"rows":[{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653,"area":"inference"},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006,"area":"inference"},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843,"area":"inference"},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637,"area":"inference"},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617,"area":"inference"},{"id":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526,"area":"inference"},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439,"area":"inference"},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288,"area":"inference"},{"id":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269,"area":"inference"},{"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":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2308.16369","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","created":"2023-08-31","cited_by_count":193,"area":"inference"},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150,"area":"inference"},{"id":"2305.05920","title":"Fast Distributed Inference Serving for Large Language Models","created":"2023-05-10","cited_by_count":145,"area":"inference"},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2312.04985","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","created":"2023-12-08","cited_by_count":119,"area":"inference"},{"id":"2402.05109","title":"Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding","created":"2024-02-07","cited_by_count":117,"area":"inference"},{"id":"2404.09526","title":"LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism","created":"2024-04-15","cited_by_count":112,"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":"2402.18096","title":"No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization","created":"2024-02-28","cited_by_count":101,"area":"inference"},{"id":"2407.15891","title":"RazorAttention: Efficient KV Cache Compression Through Retrieval Heads","created":"2024-07-22","cited_by_count":100,"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":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2401.17644","title":"BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems","created":"2024-01-31","cited_by_count":87,"area":"inference"},{"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":"2412.01827","title":"RandAR: Decoder-only Autoregressive Visual Generation in Random Orders","created":"2024-12-02","cited_by_count":83,"area":"inference"},{"id":"2306.06000","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","created":"2023-06-09","cited_by_count":81,"area":"inference"},{"id":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75,"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":"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":"2403.00835","title":"CLLMs: Consistency Large Language Models","created":"2024-02-28","cited_by_count":72,"area":"inference"},{"id":"2410.06916","title":"SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration","created":"2024-10-09","cited_by_count":72,"area":"inference"},{"id":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2404.18911","title":"Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting","created":"2024-04-29","cited_by_count":58,"area":"inference"},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2406.03482","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","created":"2024-06-05","cited_by_count":52,"area":"inference"},{"id":"2410.03111","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","created":"2024-10-04","cited_by_count":51,"area":"inference"},{"id":"2311.13581","title":"PaSS: Parallel Speculative Sampling","created":"2023-11-22","cited_by_count":49,"area":"inference"},{"id":"2408.03675","title":"NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time","created":"2024-08-07","cited_by_count":43,"area":"inference"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"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":"2402.06262","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","created":"2024-02-09","cited_by_count":32,"area":"inference"},{"id":"2406.02657","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","created":"2024-06-04","cited_by_count":32,"area":"inference"},{"id":"2401.06706","title":"Multi-Candidate Speculative Decoding","created":"2024-01-12","cited_by_count":31,"area":"inference"},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2406.07056","title":"Effectively Compress KV Heads for LLM","created":"2024-06-11","cited_by_count":30,"area":"inference"},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29,"area":"inference"},{"id":"2402.14160","title":"Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement","created":"2024-02-21","cited_by_count":27,"area":"inference"},{"id":"2410.17897","title":"Value Residual Learning","created":"2024-10-23","cited_by_count":27,"area":"inference"},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"id":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2401.06761","title":"APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding","created":"2024-01-12","cited_by_count":24,"area":"inference"},{"id":"2502.07864","title":"TransMLA: Multi-Head Latent Attention Is All You Need","created":"2025-02-11","cited_by_count":23,"area":"inference"},{"id":"2404.00242","title":"DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference","created":"2024-03-30","cited_by_count":19,"area":"inference"},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2410.13212","title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","created":"2024-10-17","cited_by_count":19,"area":"inference"},{"id":"2505.10938","title":"Accurate KV Cache Quantization with Outlier Tokens Tracing","created":"2025-05-16","cited_by_count":18,"area":"inference"},{"id":"2410.14442","title":"A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference","created":"2024-10-18","cited_by_count":17,"area":"inference"},{"id":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17,"area":"inference"},{"id":"2412.17483","title":"A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression","created":"2024-12-23","cited_by_count":17,"area":"inference"},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16,"area":"inference"},{"id":"2505.24357","title":"ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration","created":"2025-05-30","cited_by_count":16,"area":"inference"},{"id":"2407.15309","title":"vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving","created":"2024-07-22","cited_by_count":15,"area":"inference"},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15,"area":"inference"},{"id":"2602.21548","title":"DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference","created":"2026-02-25","cited_by_count":15,"area":"inference"},{"id":"2407.11798","title":"PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation","created":"2024-07-16","cited_by_count":14,"area":"inference"},{"id":"2503.18599","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","created":"2025-03-24","cited_by_count":14,"area":"inference"},{"id":"2505.20334","title":"Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query","created":"2025-05-24","cited_by_count":14,"area":"inference"},{"id":"2605.07721","title":"Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models","created":"2026-05-08","cited_by_count":14,"area":"inference"},{"id":"2403.08058","title":"CHAI: Clustered Head Attention for Efficient LLM Inference","created":"2024-03-12","cited_by_count":13,"area":"inference"},{"id":"2410.12876","title":"In-context KV-Cache Eviction for LLMs via Attention-Gate","created":"2024-10-15","cited_by_count":13,"area":"inference"},{"id":"2601.04359","title":"PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache","created":"2026-01-07","cited_by_count":13,"area":"inference"},{"id":"2602.01719","title":"COMI: Coarse-to-fine Context Compression via Marginal Information Gain","created":"2026-02-02","cited_by_count":13,"area":"inference"},{"id":"2406.16758","title":"Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters","created":"2024-06-24","cited_by_count":12,"area":"inference"},{"id":"2503.07518","title":"TokenButler: Token Importance is Predictable","created":"2025-03-10","cited_by_count":12,"area":"inference"},{"id":"2410.18234","title":"Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits","created":"2024-10-23","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":"2511.20172","title":"Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management","created":"2025-11-25","cited_by_count":11,"area":"inference"},{"id":"2412.02252","title":"Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity","created":"2024-12-03","cited_by_count":10,"area":"inference"},{"id":"2412.12706","title":"More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression","created":"2024-12-17","cited_by_count":10,"area":"inference"},{"id":"2502.00527","title":"PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration","created":"2025-02-01","cited_by_count":10,"area":"inference"},{"id":"2505.21487","title":"Hardware-Efficient Attention for Fast Decoding","created":"2025-05-27","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":"2512.05916","title":"KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity","created":"2025-12-05","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":"2502.13652","title":"C2T: A Classifier-Based Tree Construction Method in Speculative Decoding","created":"2025-02-19","cited_by_count":9,"area":"inference"},{"id":"2503.16163","title":"SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs","created":"2025-03-20","cited_by_count":9,"area":"inference"},{"id":"2507.06517","title":"SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers","created":"2025-07-09","cited_by_count":9,"area":"inference"},{"id":"2508.16134","title":"CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing","created":"2025-08-22","cited_by_count":9,"area":"inference"},{"id":"2509.15763","title":"UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression","created":"2025-09-19","cited_by_count":9,"area":"inference"},{"id":"2410.01028","title":"Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity","created":"2024-10-01","cited_by_count":8,"area":"inference"},{"id":"2503.10714","title":"ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs","created":"2025-03-13","cited_by_count":8,"area":"inference"},{"id":"2503.18773","title":"BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache","created":"2025-03-24","cited_by_count":8,"area":"inference"},{"id":"2505.12942","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","created":"2025-05-19","cited_by_count":8,"area":"inference"},{"id":"2403.08845","title":"Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs","created":"2024-03-13","cited_by_count":7,"area":"inference"},{"id":"2404.15949","title":"CORM: Cache Optimization with Recent Message for Large Language Model Inference","created":"2024-04-24","cited_by_count":7,"area":"inference"},{"id":"2410.15252","title":"Lossless KV Cache Compression to 2%","created":"2024-10-20","cited_by_count":7,"area":"inference"}],"next_cursor":"100"}