{"total":71,"rows":[{"id":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"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":"2502.06888","title":"Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline","created":"2025-02-09","cited_by_count":21,"area":"moe"},{"id":"2504.15299","title":"D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving","created":"2025-04-17","cited_by_count":20,"area":"moe"},{"id":"2410.17954","title":"ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling","created":"2024-10-23","cited_by_count":19,"area":"moe"},{"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":"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":"2504.05897","title":"HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference","created":"2025-04-08","cited_by_count":16,"area":"moe"},{"id":"2503.06433","title":"Seesaw: High-throughput LLM Inference via Model Re-sharding","created":"2025-03-09","cited_by_count":15,"area":"inference"},{"id":"2412.00099","title":"Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference","created":"2024-11-27","cited_by_count":14,"area":"moe"},{"id":"2501.10375","title":"DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference","created":"2024-12-16","cited_by_count":14,"area":"moe"},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11,"area":"moe"},{"id":"2511.14102","title":"MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts","created":"2025-11-18","cited_by_count":11,"area":"moe"},{"id":"2505.05950","title":"FloE: On-the-Fly MoE Inference on Memory-constrained GPU","created":"2025-05-09","cited_by_count":9,"area":"moe"},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2509.23638","title":"LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers","created":"2025-09-28","cited_by_count":8,"area":"moe"},{"id":"2407.14417","title":"Mixture of Experts with Mixture of Precisions for Tuning Quality of Service","created":"2024-07-19","cited_by_count":7,"area":"moe"},{"id":"2508.12851","title":"Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement","created":"2025-08-18","cited_by_count":7,"area":"moe"},{"id":"2503.09716","title":"MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching","created":"2025-03-12","cited_by_count":6,"area":"moe"},{"id":"2510.05497","title":"Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference","created":"2025-10-07","cited_by_count":6,"area":"moe"},{"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":"2603.09983","title":"MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios","created":"2026-02-12","cited_by_count":5,"area":"moe"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2601.21198","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","created":"2026-01-29","cited_by_count":4,"area":"moe"},{"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":"2512.17073","title":"Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation","created":"2025-12-18","cited_by_count":3,"area":"moe"},{"id":"2605.27081","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2608.16157","title":"FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution","created":"2026-08-17","cited_by_count":3,"area":"moe"},{"id":"2502.11417","title":"DiSCo: Device-Server Collaborative LLM-Based Text Streaming Services","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2512.04476","title":"Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems","created":"2025-12-04","cited_by_count":2,"area":"moe"},{"id":"2602.03495","title":"DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs","created":"2026-02-03","cited_by_count":2,"area":"moe"},{"id":"2603.19172","title":"DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge","created":"2026-03-19","cited_by_count":2,"area":"moe"},{"id":"2605.02960","title":"MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving","created":"2026-05-03","cited_by_count":2,"area":"moe"},{"id":"2605.20179","title":"TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload","created":"2026-05-19","cited_by_count":2,"area":"moe"},{"id":"2606.10493","title":"Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design","created":"2026-06-09","cited_by_count":2,"area":"moe"},{"id":"2607.08780","title":"Sticky Routing: Training MoE Models for Memory-Efficient Inference","created":"2026-06-12","cited_by_count":2,"area":"moe"},{"id":"2607.24434","title":"DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference","created":"2026-07-27","cited_by_count":2,"area":"moe"},{"id":"2506.01827","title":"Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.14715","title":"Exploring the Dynamic Scheduling Space of Real-Time Generative AI Applications on Emerging Heterogeneous Systems","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2509.25853","title":"SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV","created":"2025-09-30","cited_by_count":1,"area":"inference"},{"id":"2512.16473","title":"Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems","created":"2025-12-18","cited_by_count":1,"area":"moe"},{"id":"2512.21487","title":"Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism","created":"2025-12-25","cited_by_count":1,"area":"moe"},{"id":"2601.17063","title":"FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices","created":"2026-01-22","cited_by_count":1,"area":"moe"},{"id":"2606.21428","title":"Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study","created":"2026-06-19","cited_by_count":1,"area":"moe"},{"id":"2606.29982","title":"Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference","created":"2026-06-29","cited_by_count":1,"area":"moe"},{"id":"2608.15919","title":"Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery","created":"2026-08-16","cited_by_count":1,"area":"rag"},{"id":"2608.18261","title":"Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement Study","created":"2026-08-18","cited_by_count":1,"area":"moe"},{"id":"2505.06481","title":"QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration","created":"2025-05-10","cited_by_count":0,"area":"moe"},{"id":"2508.07329","title":"Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative","created":"2025-08-10","cited_by_count":0,"area":"moe"},{"id":"2601.03992","title":"A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems","created":"2026-01-07","cited_by_count":0,"area":"moe"},{"id":"2603.01058","title":"TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading","created":"2026-03-01","cited_by_count":0,"area":"moe"},{"id":"2605.05819","title":"HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.05899","title":"VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2605.17889","title":"CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution","created":"2026-05-18","cited_by_count":0,"area":"moe"},{"id":"2605.19593","title":"Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption","created":"2026-05-19","cited_by_count":0,"area":"inference"},{"id":"2607.10183","title":"Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.14333","title":"Beyond Capacity: Scalable MoE LLM Inference via High-Bandwidth Flash with Direct GPU and HBM Paths","created":"2026-08-14","cited_by_count":0,"area":"moe"},{"id":"2608.15383","title":"Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference","created":"2026-08-15","cited_by_count":0,"area":"moe"},{"id":"2609.13486","title":"Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.13537","title":"Dynamic HBM Repartitioning for Multi-Turn MoE Serving","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.14507","title":"Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.14643","title":"BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.34077","title":"MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.35882","title":"GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2609.36222","title":"BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.38090","title":"Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging","created":"2026-09-29","cited_by_count":0,"area":"moe"},{"id":"2610.15417","title":"SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference","created":"2026-10-11","cited_by_count":0,"area":"moe"},{"id":"2610.16890","title":"FORGE: Procedural Weight Generation for Sparse MoE Inference","created":"2026-10-12","cited_by_count":0,"area":"moe"}],"next_cursor":null}