{"total":92,"rows":[{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272,"area":"inference"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2406.19707","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","created":"2024-06-28","cited_by_count":245,"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":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"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":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"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":"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":"2502.07578","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":"2312.14972","title":"Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production","created":"2023-12-20","cited_by_count":21,"area":null},{"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":"2408.06003","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":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2501.11211","title":"Ditto: Accelerating Diffusion Model via Temporal Value Similarity","created":"2025-01-20","cited_by_count":18,"area":"diffusion"},{"id":"2411.15707","title":"Nimbus: Secure and Efficient Two-Party Inference for Transformers","created":"2024-11-24","cited_by_count":16,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","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":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"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":"2505.06901","title":"Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression","created":"2025-05-11","cited_by_count":14,"area":null},{"id":"2401.02643","title":"Training and Serving System of Foundation Models: A Comprehensive Survey","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2404.04748","title":"Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind","created":"2024-04-06","cited_by_count":11,"area":null},{"id":"2510.14557","title":"MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving","created":"2025-10-16","cited_by_count":11,"area":"inference"},{"id":"2411.15982","title":"Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"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":"2412.01129","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","cited_by_count":9,"area":null},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","cited_by_count":9,"area":null},{"id":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2502.05376","title":"LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference","created":"2025-02-07","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":"2411.16158","title":"MixPE: Quantization and Hardware Co-design for Efficient LLM Inference","created":"2024-11-25","cited_by_count":5,"area":"inference"},{"id":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2505.10909","title":"Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2508.16785","title":"Interpreting the Effects of Quantization on LLMs","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.16040","title":"Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing","created":"2025-10-16","cited_by_count":5,"area":"inference"},{"id":"2406.13868","title":"SDQ: Sparse Decomposed Quantization for LLM Inference","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2501.13331","title":"Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2503.07654","title":"MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.21670","title":"Rethinking the Outlier Distribution in Large Language Models: An In-depth Study","created":"2025-05-27","cited_by_count":4,"area":"lr"},{"id":"2603.22370","title":"FAAR: Format-Aware Adaptive Rounding for NVFP4","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2405.08965","title":"MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2409.05227","title":"BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2512.14661","title":"Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models","created":"2025-12-16","cited_by_count":3,"area":"inference"},{"id":"2601.20706","title":"NPU Design for Diffusion Language Model Inference","created":"2026-01-28","cited_by_count":3,"area":"diffusion"},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2508.15806","title":"REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression","created":"2025-08-14","cited_by_count":2,"area":"lr"},{"id":"2511.21910","title":"Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2605.24144","title":"EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2607.28150","title":"SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer","created":"2026-07-30","cited_by_count":2,"area":"inference"},{"id":"2307.13365","title":"Pay Attention to What You Need","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2503.12988","title":"ROMA: a Read-Only-Memory-based Accelerator for QLoRA-based On-Device LLM","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.19746","title":"FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2507.09616","title":"MLoRQ: Bridging Low-Rank and Quantization for Transformer Compression","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2510.11400","title":"FedHybrid: Breaking the Memory Wall of Federated Learning via Hybrid Tensor Management","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.18525","title":"From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing","created":"2025-10-21","cited_by_count":1,"area":"inference"},{"id":"2512.03608","title":"KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing","created":"2025-12-03","cited_by_count":1,"area":"inference"},{"id":"2601.20317","title":"VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.20662","title":"TOM: A Ternary Read-only Memory Accelerator for LLM-powered Edge Intelligence","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.12782","title":"OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2607.15846","title":"DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.24148","title":"A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference","created":"2026-07-27","cited_by_count":1,"area":"vla"},{"id":"2608.25053","title":"Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2311.14114","title":"SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2405.15346","title":"BiSup: Bidirectional Quantization Error Suppression for Large Language Models","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2502.19662","title":"HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.05893","title":"LightNobel: Improving Sequence Length Limitation in Protein Structure Prediction Model via Adaptive Activation Quantization","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2510.26008","title":"Detecting Anomalies in Machine Learning Infrastructure via Hardware Telemetry","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2511.07665","title":"FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2512.14481","title":"SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.12962","title":"TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2604.17720","title":"FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2607.08993","title":"StreamDQ: Near-Memory Weight DeQuantization in Custom HBM for Scalable AI Inference Acceleration","created":"2026-07-09","cited_by_count":0,"area":"inference"},{"id":"2607.27694","title":"GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference","created":"2026-07-30","cited_by_count":0,"area":"inference"},{"id":"2608.15531","title":"FlashQuant: Sparse-Dense Fusion for Memory-Efficient Outlier-Aware LLM Inference","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.00450","title":"HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.04724","title":"FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.12208","title":"Vortex: Bridging Extreme Compression and Efficient LLM Inference","created":"2026-09-10","cited_by_count":0,"area":"inference"},{"id":"2609.19683","title":"MiX: Micro-Inverted-Scaling for End-to-End Low-Bit Vision-Language Model Acceleration","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2610.00465","title":"AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}