{"total":106,"rows":[{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370,"area":"inference"},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331,"area":"inference"},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2405.04532","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","created":"2024-05-07","cited_by_count":208,"area":"inference"},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164,"area":"inference"},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79,"area":null},{"id":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"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":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51,"area":null},{"id":"2209.10797","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","created":"2022-09-22","cited_by_count":48,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40,"area":null},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"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":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","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":"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":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","cited_by_count":26,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2303.07470","title":"X-Former: In-Memory Acceleration of Transformers","created":"2023-03-13","cited_by_count":25,"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":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"area":null},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"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":"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":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15,"area":"distill"},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2106.01335","title":"On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2207.05022","title":"STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining","created":"2022-07-11","cited_by_count":14,"area":null},{"id":"2311.16442","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","created":"2023-11-28","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":"2209.00606","title":"Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation","created":"2022-09-01","cited_by_count":12,"area":null},{"id":"2503.10135","title":"Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding","created":"2025-03-13","cited_by_count":9,"area":"inference"},{"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":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","cited_by_count":7,"area":null},{"id":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2401.11851","title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2412.04180","title":"SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2210.15184","title":"Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models","created":"2022-10-27","cited_by_count":5,"area":"distill"},{"id":"2306.00014","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","created":"2023-05-30","cited_by_count":5,"area":null},{"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":"2507.04610","title":"any4: Learned 4-bit Numeric Representation for LLMs","created":"2025-07-07","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":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2603.25284","title":"SliderQuant: Accurate Post-Training Quantization for LLMs","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2210.16621","title":"Empirical Evaluation of Post-Training Quantization Methods for Language Tasks","created":"2022-10-29","cited_by_count":4,"area":null},{"id":"2402.01911","title":"From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2403.20137","title":"Accurate Block Quantization in LLMs with Outliers","created":"2024-03-29","cited_by_count":4,"area":"inference"},{"id":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2104.08335","title":"Demystifying BERT: Implications for Accelerator Design","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2209.09815","title":"Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation","created":"2022-09-20","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":"2510.25739","title":"Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2210.05470","title":"Block Format Error Bounds and Optimal Block Size Selection","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2306.11800","title":"Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2307.15517","title":"A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling Formats","created":"2023-07-28","cited_by_count":2,"area":"inference"},{"id":"2309.05210","title":"Understanding the Impact of Post-Training Quantization on Large Language Models","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2406.00061","title":"STAT: Shrinking Transformers After Training","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2406.16299","title":"Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2410.20046","title":"DQRM: Deep Quantized Recommendation Models","created":"2024-10-26","cited_by_count":2,"area":null},{"id":"2509.03228","title":"NeurStore: Efficient In-database Deep Learning Model Management System","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2604.18137","title":"AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization","created":"2026-04-20","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":"2103.14493","title":"RCT: Resource Constrained Training for Edge AI","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2310.07911","title":"Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2310.17723","title":"ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2503.17783","title":"Energy-Aware LLMs: A step towards sustainable AI for downstream applications","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2505.08620","title":"Resource-Efficient Language Models: Quantization for Fast and Accessible Inference","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2210.05111","title":"Deep learning model compression using network sensitivity and gradients","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2211.06982","title":"FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs","created":"2022-11-13","cited_by_count":0,"area":null},{"id":"2304.02481","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2310.03424","title":"Neural Language Model Pruning for Automatic Speech Recognition","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2407.15508","title":"Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2502.00047","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","created":"2025-01-28","cited_by_count":0,"area":null}],"next_cursor":"100"}