Cover Image

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Ning-Chi, Chang, Chi-Chih, Lin, Wei-Cheng, Taka, Endri, Marculescu, Diana, Wu, Kai-Chiang
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration
by: Taka, Endri, et al.
Published: (2025)

Efficient Approaches for GEMM Acceleration on Leading AI-Optimized FPGAs
by: Taka, Endri, et al.
Published: (2024)

NM-SpMM: Accelerating Matrix Multiplication Using N:M Sparsity with GPGPU
by: Ma, Cong, et al.
Published: (2025)

Quamba: A Post-Training Quantization Recipe for Selective State Space Models
by: Chiang, Hung-Yueh, et al.
Published: (2024)

Striking the Balance: GEMM Performance Optimization Across Generations of Ryzen AI NPUs
by: Taka, Endri, et al.
Published: (2025)

GAMA: High-Performance GEMM Acceleration on AMD Versal ML-Optimized AI Engines
by: Mhatre, Kaustubh, et al.
Published: (2025)

Spatial Re-parameterization for N:M Sparsity
by: Zhang, Yuxin, et al.
Published: (2023)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
by: Chiang, Hung-Yueh, et al.
Published: (2025)

Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
by: Bambhaniya, Abhimanyu Rajeshkumar, et al.
Published: (2024)

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models
by: Chi, Tien-Yu, et al.
Published: (2025)

V"Mean"ba: Visual State Space Models only need 1 hidden dimension
by: Chi, Tien-Yu, et al.
Published: (2024)

UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
by: Chiang, Hung-Yueh, et al.
Published: (2025)

DARE: Diffusion Language Model Activation Reuse for Efficient Inference
by: Frumkin, Natalia, et al.
Published: (2026)

MaxQ: Multi-Axis Query for N:M Sparsity Network
by: Xiang, Jingyang, et al.
Published: (2023)

Efficient Column-Wise N:M Pruning on RISC-V CPU
by: Chu, Chi-Wei, et al.
Published: (2025)

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
by: Chmiel, Brian, et al.
Published: (2022)

Toward Efficient Permutation for Hierarchical N:M Sparsity on GPUs
by: Yu, Seungmin, et al.
Published: (2024)

Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
by: Ramachandran, Akshat, et al.
Published: (2025)

E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
by: Li, Yun, et al.
Published: (2023)

Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
by: Wang, Pei-Shuo, et al.
Published: (2025)

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models
by: An, Tai, et al.
Published: (2025)

SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Diverse Edge Devices via Hardware-Aware Evolutionary Search
by: Chiang, Hung-Yueh, et al.
Published: (2024)

MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
by: Sun, Yan, et al.
Published: (2025)

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
by: Alanova, Shirin, et al.
Published: (2025)

Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
by: Frumkin, Natalia, et al.
Published: (2023)

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers
by: Hsu, Chih-Chung, et al.
Published: (2026)

xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
by: Chang, Chi-Chih, et al.
Published: (2025)

ELANA: A Simple Energy and Latency Analyzer for LLMs
by: Chiang, Hung-Yueh, et al.
Published: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
by: Zou, Chang, et al.
Published: (2024)

Can Asymmetric Tile Buffering Be Beneficial?
by: Wang, Chengyue, et al.
Published: (2025)

Palu: Compressing KV-Cache with Low-Rank Projection
by: Chang, Chi-Chih, et al.
Published: (2024)

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
by: Huang, Weizhong, et al.
Published: (2025)

SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
by: Liang, Feng, et al.
Published: (2022)

DreamDDP: Accelerating Data Parallel Distributed LLM Training with Layer-wise Scheduled Partial Synchronization
by: Tang, Zhenheng, et al.
Published: (2025)

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training
by: Wu, Xueqing, et al.
Published: (2026)

FPGA Co-Design for Efficient N:M Sparse and Quantized Model Inference
by: Hsieh, Fen-Yu, et al.
Published: (2025)

Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
by: Menn, Dennis, et al.
Published: (2024)

P‐144: Ultra‐High Brightness Quantum‐Dot Light‐Emitting Diodes with ZnO Nanoparticles Charge‐Control Layer
by: Chih-Jung Chen, et al.
Published: (2025)

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
by: Jia, Ding, et al.
Published: (2024)

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference
by: Li, Guandong
Published: (2026)