{"total":147,"rows":[{"id":"2405.05465","title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","created":"2024-05-08","cited_by_count":117,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"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":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55,"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":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2503.08311","title":"Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference","created":"2025-03-11","cited_by_count":33,"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":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"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":"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":"2501.04437","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","created":"2025-01-08","cited_by_count":23,"area":null},{"id":"2501.14794","title":"Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference","created":"2025-01-11","cited_by_count":22,"area":null},{"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":"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":"2412.14590","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","created":"2024-12-19","cited_by_count":16,"area":null},{"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":"2505.11329","title":"TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference","created":"2025-05-16","cited_by_count":14,"area":null},{"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":"2409.19245","title":"Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning","created":"2024-09-28","cited_by_count":12,"area":null},{"id":"2410.00531","title":"TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices","created":"2024-10-01","cited_by_count":11,"area":null},{"id":"2502.11256","title":"Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View","created":"2025-02-16","cited_by_count":11,"area":null},{"id":"2504.06667","title":"Toward Holistic Evaluation of Recommender Systems Powered by Generative Models","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2606.24773","title":"Posterior Refinement: Fast Language Generation via Any-Order Flow Maps","created":"2026-06-23","cited_by_count":11,"area":null},{"id":"2404.09529","title":"Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models","created":"2024-04-15","cited_by_count":10,"area":null},{"id":"2508.14544","title":"Adaptively Robust LLM Inference Optimization under Prediction Uncertainty","created":"2025-08-20","cited_by_count":10,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2412.04504","title":"Multi-Bin Batching for Increasing LLM Inference Throughput","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2508.16712","title":"Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective","created":"2025-08-22","cited_by_count":9,"area":null},{"id":"2504.11750","title":"Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures","created":"2025-04-16","cited_by_count":8,"area":null},{"id":"2403.04311","title":"Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2503.22562","title":"Niyama : Breaking the Silos of LLM Inference Serving","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2410.12168","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2410.15653","title":"Opportunities and Challenges of Generative-AI in Finance","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2510.08544","title":"SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2603.10088","title":"ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping","created":"2026-03-10","cited_by_count":6,"area":null},{"id":"2608.09444","title":"Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching","created":"2026-08-10","cited_by_count":6,"area":null},{"id":"2410.01228","title":"ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2503.02354","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2503.07545","title":"Queueing, Predictions, and LLMs: Challenges and Open Problems","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.16397","title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2507.17769","title":"PolyServe: Efficient Multi-SLO Serving at Scale","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2508.19559","title":"Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2510.06126","title":"lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2601.00397","title":"Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2606.07684","title":"Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2408.07802","title":"Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2409.15104","title":"PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2410.17840","title":"Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2501.14784","title":"DeServe: Towards Affordable Offline LLM Inference via Decentralization","created":"2025-01-04","cited_by_count":4,"area":null},{"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":"2411.15997","title":"Ensuring Fair LLM Serving Amid Diverse Applications","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2503.10666","title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2503.19779","title":"PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2507.21276","title":"LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2509.12610","title":"ScaleDoc: Scaling LLM-based Predicates over Large Document Collections","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2602.08722","title":"QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.15965","title":"MoLoRA: Composable Specialization via Per-Token Adapter Routing","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2605.30218","title":"MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2404.15153","title":"Performance Characterization of Expert Router for Scalable LLM Inference","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2502.11417","title":"DiSCo: Device-Server Collaborative LLM-Based Text Streaming Services","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.15763","title":"Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2503.13737","title":"AccelGen: Heterogeneous SLO-Guaranteed High-Throughput LLM Inference Serving for Diverse Applications","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2512.16134","title":"Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2602.05712","title":"Towards Green AI: Decoding the Energy of LLM Inference in Software Development","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.16068","title":"Resource Consumption Threats in Large Language Models","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2606.00288","title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.28565","title":"KernelSight-LM: A Kernel-Level LLM Inference Simulator","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2410.18701","title":"BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2410.23668","title":"Kernel Looping: Eliminating Synchronization Boundaries for Peak Inference Performance","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2501.05408","title":"Tempo: Compiled Dynamic Deep Learning with Symbolic Dependence Graphs","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2505.14468","title":"ServerlessLoRA: Enabling Low-Latency Serverless Multi-LoRA Serving","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.15909","title":"Is (Selective) Round-To-Nearest Quantization All You Need?","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.16881","title":"CASTILLO: Characterizing Response Length Distributions of Large Language Models","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.14851","title":"Efficient Serving of LLM Applications with Probabilistic Demand Modeling","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2510.13668","title":"STAR: Decode-Phase Rescheduling for LLM Inference","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.00847","title":"You Only Need Your Transformer 25% of the Time: Meaning-First Execution for Eliminating Unnecessary Inference","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2601.06940","title":"VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenance","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.09258","title":"LatencyPrism: Online Non-intrusive Latency Sculpting for SLO-Guaranteed LLM Inference","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2603.13314","title":"Linear Predictability of Attention Heads in Large Language Models","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.02522","title":"Opal: Private Memory for Personal AI","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.08075","title":"Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.22733","title":"HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2607.11368","title":"Decomposing Runtime, Kernel, and Quantization Speedups via a Matched FP16 Intermediate: A Hardware-Conditioned Case Study on Four NVIDIA RTX A5000 GPUs","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.18253","title":"Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.26491","title":"LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2609.12923","title":"Dissecting GPU Utilization for LLM Inference on Nvidia Hopper","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2609.25405","title":"Efficient Iterative Retrieval with Heterogeneous Batching","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2610.05305","title":"Characterizing Parallelism Strategies in LLM Inference: Fundamental Compute-Communication Trade-offs","created":"2026-10-04","cited_by_count":1,"area":null},{"id":"2403.16125","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2510.24801","title":"Fortytwo: Swarm Inference with Peer-Ranked Consensus","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2511.00101","title":"Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.00603","title":"EPARA: Parallelizing Categorized AI Inference in Edge Clouds","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2512.10990","title":"Dora: QoE-Aware Hybrid Parallelism for Distributed Edge AI","created":"2025-12-09","cited_by_count":0,"area":null}],"next_cursor":"100"}