{"total":112,"rows":[{"id":"2408.15792","title":"Efficient LLM Scheduling by Learning to Rank","created":"2024-08-28","cited_by_count":85,"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":"2410.01035","title":"Don't Stop Me Now: Embedding Based Scheduling for LLMs","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2502.20576","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","created":"2025-02-27","cited_by_count":35,"area":null},{"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":"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":"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":"2502.00722","title":"Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs","created":"2025-02-02","cited_by_count":22,"area":"inference"},{"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":"2508.18298","title":"Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms","created":"2025-08-22","cited_by_count":18,"area":"agents"},{"id":"2411.08982","title":"Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection","created":"2024-11-13","cited_by_count":16,"area":"moe"},{"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":"2410.15761","title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","created":"2024-10-21","cited_by_count":15,"area":null},{"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":"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":"2512.03416","title":"TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity","created":"2025-12-03","cited_by_count":12,"area":"inference"},{"id":"2604.15039","title":"Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter","created":"2026-04-16","cited_by_count":11,"area":"inference"},{"id":"2409.11416","title":"The Unseen AI Disruptions for Power Grids: LLM-Induced Transients","created":"2024-09-09","cited_by_count":10,"area":null},{"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":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2411.17741","title":"Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2504.15465","title":"LithOS: An Operating System for Efficient Machine Learning on GPUs","created":"2025-04-21","cited_by_count":9,"area":null},{"id":"2512.13525","title":"Janus: Disaggregating Attention and Experts for Scalable MoE Inference","created":"2025-12-15","cited_by_count":8,"area":"moe"},{"id":"2503.22562","title":"Niyama : Breaking the Silos of LLM Inference Serving","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2506.02006","title":"MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing","created":"2025-05-24","cited_by_count":6,"area":"inference"},{"id":"2512.05951","title":"Trusted AI Agents in the Cloud","created":"2025-12-05","cited_by_count":6,"area":"agents"},{"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":"2605.00528","title":"SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2504.14775","title":"gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling","created":"2025-04-21","cited_by_count":5,"area":"inference"},{"id":"2509.10371","title":"Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2511.22880","title":"Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems","created":"2025-11-28","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":"2603.20224","title":"Beyond Test-Time Compute Strategies: Advocating Energy-per-Token in LLM Inference","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2604.09048","title":"Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures","created":"2026-04-10","cited_by_count":5,"area":"inference"},{"id":"2502.09921","title":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","created":"2025-02-14","cited_by_count":4,"area":"inference"},{"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":"2510.08055","title":"From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill","created":"2025-10-09","cited_by_count":4,"area":"moe"},{"id":"2411.14458","title":"Improving training time and GPU utilization in geo-distributed language model training","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2504.09345","title":"MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints","created":"2025-04-12","cited_by_count":3,"area":"moe"},{"id":"2505.17138","title":"RAP: Runtime Adaptive Pruning for LLM Inference","created":"2025-05-22","cited_by_count":3,"area":"inference"},{"id":"2601.17654","title":"Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training","created":"2026-01-25","cited_by_count":3,"area":null},{"id":"2602.12151","title":"OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration","created":"2026-02-12","cited_by_count":3,"area":"inference"},{"id":"2605.05467","title":"Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism","created":"2026-05-06","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":"2508.16646","title":"Equinox: Holistic Fair Scheduling in Serving Large Language Models","created":"2025-08-19","cited_by_count":2,"area":"inference"},{"id":"2510.03243","title":"Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2601.08539","title":"Reducing Compute Waste in LLMs through Kernel-Level DVFS","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2601.08833","title":"Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications","created":"2025-11-14","cited_by_count":2,"area":"inference"},{"id":"2604.09611","title":"Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows","created":"2026-03-12","cited_by_count":2,"area":"inference"},{"id":"2605.04357","title":"Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs","created":"2026-05-05","cited_by_count":2,"area":"inference"},{"id":"2606.23001","title":"EnerInfer: Energy-Aware On-Device LLM Inference","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2608.28044","title":"Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms","created":"2026-08-28","cited_by_count":2,"area":"moe"},{"id":"2412.03716","title":"A Water Efficiency Dataset for African Data Centers","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2501.12162","title":"AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding","created":"2025-01-21","cited_by_count":1,"area":"inference"},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2502.11723","title":"Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2504.20348","title":"CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices","created":"2025-04-29","cited_by_count":1,"area":"agents"},{"id":"2505.14468","title":"ServerlessLoRA: Enabling Low-Latency Serverless Multi-LoRA Serving","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2510.02822","title":"FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.21970","title":"Performance Trade-offs of Optimizing Small Language Models for E-Commerce","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2512.25065","title":"Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.05109","title":"Nalar: An agent serving framework","created":"2026-01-08","cited_by_count":1,"area":"agents"},{"id":"2603.06350","title":"MoEless: Efficient MoE LLM Serving via Serverless Computing","created":"2026-03-06","cited_by_count":1,"area":"moe"},{"id":"2604.16682","title":"KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving","created":"2026-04-17","cited_by_count":1,"area":"agents"},{"id":"2605.01280","title":"Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics","created":"2026-05-02","cited_by_count":1,"area":"inference"},{"id":"2607.17175","title":"LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters","created":"2026-07-19","cited_by_count":1,"area":null},{"id":"2409.06941","title":"FreeRide: Harvesting Bubbles in Pipeline Parallelism","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2506.03296","title":"APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs","created":"2025-06-03","cited_by_count":0,"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":"2510.15330","title":"BeLLMan: Controlling LLM Congestion","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.07776","title":"Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2511.22481","title":"OmniInfer: System-Wide Acceleration Techniques for Optimizing LLM Serving Throughput and Latency","created":"2025-11-27","cited_by_count":0,"area":"inference"},{"id":"2512.08365","title":"Magneton: Optimizing Energy Efficiency of ML Systems via Differential Energy Debugging","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.12928","title":"ProServe: Unified Multi-Priority Request Scheduling for LLM Serving","created":"2025-12-15","cited_by_count":0,"area":"inference"},{"id":"2602.02943","title":"3D-Learning: Diffusion-Augmented Distributionally Robust Decision-Focused Learning","created":"2026-02-03","cited_by_count":0,"area":"diffusion"},{"id":"2602.18931","title":"WANSpec: Leveraging Global Compute Capacity for LLM Inference","created":"2026-02-21","cited_by_count":0,"area":"inference"},{"id":"2603.05800","title":"StreamWise: Serving Multi-Modal Generation in Real-Time at Scale","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.06198","title":"Concentrated siting of AI data centers drives regional power-system stress under rising global compute demand","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.07472","title":"Scalable Joint Resource Allocation for SLO-Constrained LLM Inference in Heterogeneous GPU Clouds","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.27855","title":"AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.06113","title":"Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale","created":"2026-05-07","cited_by_count":0,"area":"inference"},{"id":"2605.10556","title":"EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2606.07632","title":"Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.10861","title":"From Perception to Action: Can UI Interventions Foster Sustainable LLM Chatbot","created":"2026-06-09","cited_by_count":0,"area":null},{"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":"2606.22327","title":"Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice","created":"2026-06-21","cited_by_count":0,"area":"inference"},{"id":"2606.30391","title":"Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs","created":"2026-06-29","cited_by_count":0,"area":"inference"},{"id":"2607.11211","title":"FastTPS: An Optimized Method for LLM Token Phase for AI accelerators","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.16488","title":"Auto-Scaling Heterogeneous Neural Processing Units for Energy and Cost-Efficient LLM Serving","created":"2026-07-17","cited_by_count":0,"area":"inference"},{"id":"2607.25498","title":"Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling","created":"2026-07-28","cited_by_count":0,"area":"inference"},{"id":"2608.03555","title":"Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse Attention","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2608.12915","title":"InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13499","title":"OpScale: Operator-level Provisioning and Autoscaling for LLM Serving","created":"2026-08-13","cited_by_count":0,"area":"inference"},{"id":"2608.18149","title":"TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2608.19659","title":"FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet Configuration","created":"2026-08-20","cited_by_count":0,"area":"inference"},{"id":"2608.20566","title":"AgentDecarbonizer: Carbon-Aware Execution for AI Agents","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.00442","title":"DRLM: Deep Reinforcement Learning-Based LLM Query Orchestration in Edge Environments","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.05565","title":"Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":"100"}