Cover Image

NeuronMLP: Efficient LLM Inference via Singular Value Decomposition Compression and Tiling on AWS Trainium

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Dinghong, Xu, Jierui, Yang, Weichu, Su, Pengfei, Li, Dong
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HLAT: High-quality Large Language Model Pre-trained on AWS Trainium
by: Fan, Haozheng, et al.
Published: (2024)

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
by: Song, Dinghong, et al.
Published: (2025)

NinjaLLM: Fast, Scalable and Cost-effective RAG using Amazon SageMaker and AWS Trainium and Inferentia2
by: Xue, Tengfei, et al.
Published: (2024)

ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
by: Yuan, Zhihang, et al.
Published: (2023)

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
by: Wang, Xin, et al.
Published: (2024)

Disentangling MLP Neuron Weights in Vocabulary Space
by: Avrahamy, Asaf, et al.
Published: (2026)

Adversarial Contrastive Learning for LLM Quantization Attacks
by: Song, Dinghong, et al.
Published: (2026)

EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition
by: Nasiri, Hamid, et al.
Published: (2025)

Distilling Algorithmic Reasoning from LLMs via Explaining Solution Programs
by: Li, Jierui, et al.
Published: (2024)

SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
by: Wang, Xin, et al.
Published: (2025)

Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering
by: Dong, Fangan, et al.
Published: (2026)

Dual Decomposition of Weights and Singular Value Low Rank Adaptation
by: Han, Jialong, et al.
Published: (2025)

Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
by: Sengupta, Ayan, et al.
Published: (2025)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models
by: Cao, Yang, et al.
Published: (2024)

Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product
by: Lan, Pengxiang, et al.
Published: (2025)

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
by: Su, Yi, et al.
Published: (2025)

AdaSVD: Adaptive Singular Value Decomposition for Large Language Models
by: Li, Zhiteng, et al.
Published: (2025)

A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition
by: Xiaobo, Jiang, et al.
Published: (2026)

AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming
by: Li, Jierui, et al.
Published: (2025)

NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension
by: Li, Rongzhi, et al.
Published: (2026)

Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes
by: Alipour, Mohammadsajad, et al.
Published: (2025)

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
by: Yang, Dongjie, et al.
Published: (2024)

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
by: Song, Jiwon, et al.
Published: (2025)

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity
by: Ma, Da, et al.
Published: (2024)

Optimizing Singular Spectrum for Large Language Model Compression
by: Li, Dengjie, et al.
Published: (2025)

Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
by: Li, Jingxuan, et al.
Published: (2024)

Efficient LLM-based Advertising via Model Compression and Parallel Verification
by: Dong, Wenxin, et al.
Published: (2026)

PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel
by: Yi, Jinjun, et al.
Published: (2025)

AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search
by: Li, Yu, et al.
Published: (2025)

DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference
by: Ye, Jiancai, et al.
Published: (2026)

CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values
by: Koleilat, Taha, et al.
Published: (2025)

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
by: Tian, Yuxuan, et al.
Published: (2025)

Image Compression Using Singular Value Decomposition
by: Jiang, Justin
Published: (2025)

GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression
by: Liu, Kainan, et al.
Published: (2024)

ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models
by: Li, Jierui, et al.
Published: (2023)

Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
by: Luo, Yifan, et al.
Published: (2024)

YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference
by: Wu, You, et al.
Published: (2026)

Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
by: Zheng, Li, et al.
Published: (2026)

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
by: Zhu, Kejian, et al.
Published: (2025)