{"total":558,"rows":[{"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":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2403.19708","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention","created":"2024-03-23","cited_by_count":163,"area":"inference"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126,"area":"inference"},{"id":"2405.05465","title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","created":"2024-05-08","cited_by_count":117,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"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":"2408.00741","title":"DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency","created":"2024-08-01","cited_by_count":112,"area":null},{"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":"2405.19888","title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","created":"2024-05-30","cited_by_count":99,"area":null},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"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":"2401.17644","title":"BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems","created":"2024-01-31","cited_by_count":87,"area":"inference"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2408.15792","title":"Efficient LLM Scheduling by Learning to Rank","created":"2024-08-28","cited_by_count":85,"area":"inference"},{"id":"2505.09598","title":"How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference","created":"2025-05-14","cited_by_count":76,"area":null},{"id":"2407.00023","title":"Preble: Efficient Distributed Prompt Scheduling for LLM Serving","created":"2024-05-08","cited_by_count":70,"area":"inference"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"area":null},{"id":"2403.20306","title":"Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference","created":"2024-03-29","cited_by_count":61,"area":null},{"id":"2504.15930","title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation","created":"2025-04-22","cited_by_count":61,"area":null},{"id":"2412.20993","title":"Efficiently Scaling LLM Reasoning with Certaindex","created":"2024-12-30","cited_by_count":58,"area":"lr"},{"id":"2406.01566","title":"Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow","created":"2024-06-03","cited_by_count":55,"area":null},{"id":"2507.19427","title":"Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding","created":"2025-07-25","cited_by_count":55,"area":"moe"},{"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":"2410.15332","title":"EPIC: Efficient Position-Independent Caching for Serving Large Language Models","created":"2024-10-20","cited_by_count":47,"area":null},{"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":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45,"area":null},{"id":"2409.13221","title":"Optimizing RLHF Training for Large Language Models with Stage Fusion","created":"2024-09-20","cited_by_count":43,"area":"alignment"},{"id":"2506.02634","title":"KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider","created":"2025-06-03","cited_by_count":41,"area":"inference"},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2405.14696","title":"A Declarative System for Optimizing AI Workloads","created":"2024-05-23","cited_by_count":37,"area":null},{"id":"2411.01142","title":"NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference","created":"2024-11-02","cited_by_count":37,"area":"inference"},{"id":"2409.01141","title":"Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching","created":"2024-09-02","cited_by_count":34,"area":"moe"},{"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":"2505.06371","title":"The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization","created":"2025-05-09","cited_by_count":33,"area":null},{"id":"2404.05019","title":"Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts","created":"2024-04-07","cited_by_count":32,"area":"moe"},{"id":"2504.02263","title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism","created":"2025-04-03","cited_by_count":32,"area":"moe"},{"id":"2404.14527","title":"M\\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","created":"2024-04-22","cited_by_count":31,"area":null},{"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":"2501.02600","title":"TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms","created":"2025-01-05","cited_by_count":29,"area":null},{"id":"2505.09999","title":"ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production","created":"2025-05-15","cited_by_count":29,"area":"inference"},{"id":"2407.04014","title":"Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems","created":"2024-07-04","cited_by_count":28,"area":"inference"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2408.08147","title":"P/D-Serve: Serving Disaggregated Large Language Model at Scale","created":"2024-08-15","cited_by_count":27,"area":"inference"},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25,"area":null},{"id":"2502.05370","title":"Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading","created":"2025-02-07","cited_by_count":24,"area":"moe"},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2502.09334","title":"ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments","created":"2025-02-13","cited_by_count":23,"area":"inference"},{"id":"2508.01989","title":"Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving","created":"2025-08-04","cited_by_count":23,"area":"inference"},{"id":"2501.14794","title":"Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference","created":"2025-01-11","cited_by_count":22,"area":null},{"id":"2502.00722","title":"Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs","created":"2025-02-02","cited_by_count":22,"area":"inference"},{"id":"2502.07578","title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","created":"2025-02-11","cited_by_count":22,"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":"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":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19,"area":"inference"},{"id":"2409.04992","title":"InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference","created":"2024-09-08","cited_by_count":19,"area":"inference"},{"id":"2410.02950","title":"LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2411.16102","title":"BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2501.08219","title":"Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling","created":"2025-01-14","cited_by_count":19,"area":null},{"id":"2502.07115","title":"Online Scheduling for LLM Inference with KV Cache Constraints","created":"2025-02-10","cited_by_count":19,"area":"inference"},{"id":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"id":"2504.08784","title":"SLOs-Serve: Optimized Serving of Multi-SLO LLMs","created":"2025-04-05","cited_by_count":19,"area":null},{"id":"2504.11320","title":"Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints","created":"2025-04-15","cited_by_count":19,"area":null},{"id":"2602.18397","title":"How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf","created":"2026-02-20","cited_by_count":19,"area":"vla"},{"id":"2312.05215","title":"DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs","created":"2023-12-08","cited_by_count":18,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2503.05096","title":"AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving","created":"2025-03-07","cited_by_count":18,"area":"inference"},{"id":"2504.07347","title":"Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents","created":"2025-04-10","cited_by_count":18,"area":"agents"},{"id":"2505.10938","title":"Accurate KV Cache Quantization with Outlier Tokens Tracing","created":"2025-05-16","cited_by_count":18,"area":"inference"},{"id":"2504.20068","title":"JITServe: SLO-aware LLM Serving with Imprecise Request Information","created":"2025-04-24","cited_by_count":17,"area":"inference"},{"id":"2401.16677","title":"T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives","created":"2024-01-30","cited_by_count":16,"area":null},{"id":"2501.05460","title":"Efficiently Serving Large Multimodal Models Using EPD Disaggregation","created":"2024-12-25","cited_by_count":16,"area":"mllm"},{"id":"2502.18993","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","created":"2025-02-26","cited_by_count":16,"area":"rag"},{"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":"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":"2510.27176","title":"Glia: A Human-Inspired AI for Automated Systems Design and Optimization","created":"2025-10-31","cited_by_count":16,"area":null},{"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":"2411.17651","title":"APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving","created":"2024-11-26","cited_by_count":15,"area":"inference"},{"id":"2412.11854","title":"Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference","created":"2024-12-16","cited_by_count":15,"area":"rag"},{"id":"2503.06433","title":"Seesaw: High-throughput LLM Inference via Model Re-sharding","created":"2025-03-09","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":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2503.20552","title":"Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation","created":"2025-03-26","cited_by_count":14,"area":"inference"},{"id":"2505.11329","title":"TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2512.22560","title":"RollArt: Disaggregated Multi-Task Agentic RL Training at Scale","created":"2025-12-27","cited_by_count":14,"area":"agents"},{"id":"2409.17264","title":"No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2501.12689","title":"IC-Cache: Efficient Large Language Model Serving via In-context Caching","created":"2025-01-22","cited_by_count":13,"area":null},{"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":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2512.18194","title":"TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-Scale","created":"2025-12-20","cited_by_count":13,"area":"inference"}],"next_cursor":"100"}