{"total":141,"rows":[{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386,"area":null},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591,"area":"inference"},{"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":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294,"area":null},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2406.17343","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","created":"2024-06-25","cited_by_count":94,"area":"diffusion"},{"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":"2310.16836","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","created":"2023-10-25","cited_by_count":69,"area":null},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"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":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2205.11380","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","created":"2022-05-23","cited_by_count":55,"area":null},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2403.11421","title":"FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines","created":"2024-03-18","cited_by_count":49,"area":"inference"},{"id":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2404.07947","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","created":"2024-03-15","cited_by_count":45,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","cited_by_count":38,"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":"2406.12016","title":"Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization","created":"2024-06-17","cited_by_count":33,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"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":"2305.14858","title":"Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers","created":"2023-05-24","cited_by_count":30,"area":null},{"id":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","cited_by_count":29,"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":"2306.00477","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","created":"2023-06-01","cited_by_count":26,"area":null},{"id":"2404.00928","title":"Instance-Aware Group Quantization for Vision Transformers","created":"2024-04-01","cited_by_count":25,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2405.14428","title":"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2205.12694","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2311.05161","title":"Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization","created":"2023-11-09","cited_by_count":20,"area":null},{"id":"2506.11543","title":"FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation","created":"2025-06-13","cited_by_count":19,"area":null},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2306.00458","title":"Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2309.01729","title":"Softmax Bias Correction for Quantized Generative Models","created":"2023-09-04","cited_by_count":15,"area":"diffusion"},{"id":"2202.00441","title":"Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2407.03917","title":"Timestep-Aware Correction for Quantized Diffusion Models","created":"2024-07-04","cited_by_count":13,"area":"diffusion"},{"id":"2407.08044","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2410.17174","title":"From Attention to Activation: Unravelling the Enigmas of Large Language Models","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","cited_by_count":13,"area":null},{"id":"2211.11014","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","created":"2022-11-20","cited_by_count":11,"area":"distill"},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2501.04304","title":"DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models","created":"2025-01-08","cited_by_count":11,"area":"diffusion"},{"id":"2511.06767","title":"QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations","created":"2025-11-10","cited_by_count":11,"area":null},{"id":"2211.16912","title":"Quadapter: Adapter for GPT-2 Quantization","created":"2022-11-30","cited_by_count":10,"area":null},{"id":"2302.10360","title":"Optical Transformers","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2404.02837","title":"Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2310.05079","title":"Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?","created":"2023-10-08","cited_by_count":8,"area":null},{"id":"2510.09017","title":"Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2510.10238","title":"The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2605.15208","title":"Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels","created":"2026-05-02","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":"2405.18548","title":"Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2303.05378","title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2402.17985","title":"FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2408.15301","title":"The Uniqueness of LLaMA3-70B Series with Per-Channel Quantization","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2502.18424","title":"Compressing Language Models for Specialized Domains","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2505.23277","title":"Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression","created":"2025-05-29","cited_by_count":4,"area":"rag"},{"id":"2605.25880","title":"The Quantization Benefits of Residual-Free Transformers","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2208.11945","title":"Efficient Adaptive Activation Rounding for Post-Training Quantization","created":"2022-08-25","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":"2312.00388","title":"LinguaLinked: A Distributed Large Language Model Inference System for Mobile Devices","created":"2023-12-01","cited_by_count":3,"area":"inference"},{"id":"2406.11022","title":"Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models","created":"2024-06-16","cited_by_count":3,"area":"distill"},{"id":"2411.06151","title":"Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust","created":"2024-11-09","cited_by_count":3,"area":null},{"id":"2509.22536","title":"A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2210.13086","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2307.05972","title":"Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2309.08708","title":"Vocabulary-level Memory Efficiency for Language Model Fine-tuning","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2310.04836","title":"Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2310.13315","title":"Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models","created":"2023-10-20","cited_by_count":2,"area":null}],"next_cursor":"100"}