Cover Image

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Duan, Bowen, Guo, Cong, Wei, Chiyue, Shan, Haoxuan, Fu, Yuzhe, Chen, Xinhua, Xu, Yifan, Zhang, Ziyue, Zhou, Changchun, Li, Hai, Chen, Yiran
Format:	Preprint
Published:	2026
Subjects:	Hardware Architecture Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models
by: Wei, Chiyue, et al.
Published: (2025)

FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing
by: Fu, Yuzhe, et al.
Published: (2025)

EVA: Recasting LLM Decoding into GEMM via an Efficient Vector Quantization Architecture
by: Duan, Bowen, et al.
Published: (2026)

Transitive Array: An Efficient GEMM Accelerator with Result Reuse
by: Guo, Cong, et al.
Published: (2025)

Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication
by: Shan, Haoxuan, et al.
Published: (2025)

Prosperity: Accelerating Spiking Neural Networks via Product Sparsity
by: Wei, Chiyue, et al.
Published: (2025)

Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks
by: Wei, Chiyue, et al.
Published: (2025)

Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression
by: Cheng, Feng, et al.
Published: (2025)

KLLM: Fast LLM Inference with K-Means Quantization
by: Wu, Xueying, et al.
Published: (2025)

TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs
by: Qiao, Ye, et al.
Published: (2025)

Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration
by: Chen, Peilin, et al.
Published: (2025)

End-to-End Transformer Acceleration Through Processing-in-Memory Architectures
by: Yang, Xiaoxuan, et al.
Published: (2025)

TeLLMe v2: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs
by: Qiao, Ye, et al.
Published: (2025)

FusionCIM: Accelerating LLM Inference with Fusion-Driven Computing-in-Memory Architecture
by: Xuan, Zihao, et al.
Published: (2026)

LoopLynx: A Scalable Dataflow Architecture for Efficient LLM Inference
by: Zheng, Jianing, et al.
Published: (2025)

CAMformer: Associative Memory is All You Need
by: Molom-Ochir, Tergel, et al.
Published: (2025)

SwiftKV: An Edge-Oriented Attention Algorithm and Multi-Head Accelerator for Fast, Efficient LLM Decoding
by: Zhang, Junming, et al.
Published: (2026)

PD-Swap: Prefill-Decode Logic Swapping for End-to-End LLM Inference on Edge FPGAs via Dynamic Partial Reconfiguration
by: Zhang, Yifan, et al.
Published: (2025)

D-Legion: A Scalable Many-Core Architecture for Accelerating Matrix Multiplication in Quantized LLMs
by: Abdelmaksoud, Ahmed J., et al.
Published: (2026)

AutoRAC: Automated Processing-in-Memory Accelerator Design for Recommender Systems
by: Cheng, Feng, et al.
Published: (2025)

In-Pipeline Integration of Digital In-Memory-Computing into RISC-V Vector Architecture to Accelerate Deep Learning
by: Spagnolo, Tommaso, et al.
Published: (2026)

NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing
by: Wang, Yitu, et al.
Published: (2023)

XtraMAC: An Efficient MAC Architecture for Mixed-Precision LLM Inference on FPGA
by: Yu, Feng, et al.
Published: (2026)

MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization
by: Li, Shuaiting, et al.
Published: (2024)

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
by: Huang, Zhirui, et al.
Published: (2025)

LlamaF: An Efficient Llama2 Architecture Accelerator on Embedded FPGAs
by: Xu, Han, et al.
Published: (2024)

Empowering Vector Architectures for ML: The CAMP Architecture for Matrix Multiplication
by: Nojehdeh, Mohammadreza Esmali, et al.
Published: (2025)

CompAir: Synergizing Complementary PIMs and In-Transit NoC Computation for Efficient LLM Acceleration
by: Li, Hongyi, et al.
Published: (2025)

DORA: Dataflow-Instruction Orchestration Architecture for DNN Acceleration
by: Chen, Xingzhen, et al.
Published: (2026)

VMXDOTP: A RISC-V Vector ISA Extension for Efficient Microscaling (MX) Format Acceleration
by: Wipfli, Max, et al.
Published: (2026)

M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization
by: Hu, Weiming, et al.
Published: (2026)

A Switch-Centric In-Network Architecture for Accelerating LLM Inference in Shared-Memory Network
by: Jiang, Aojie, et al.
Published: (2026)

Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM
by: Yu, Zhongkai, et al.
Published: (2024)

Energy Efficient LSTM Accelerators for Embedded FPGAs through Parameterised Architecture Design
by: Qian, Chao, et al.
Published: (2026)

Hemlet: A Heterogeneous Compute-in-Memory Chiplet Architecture for Vision Transformers with Group-Level Parallelism
by: Wang, Cong, et al.
Published: (2025)

FETTA: Flexible and Efficient Hardware Accelerator for Tensorized Neural Network Training
by: Lu, Jinming, et al.
Published: (2025)

Retrieve, Schedule, Reflect: LLM Agents for Chip QoR Optimization
by: ouyang, Yikang, et al.
Published: (2026)

From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing
by: Zhao, Yushu, et al.
Published: (2025)

FILCO: Flexible Composing Architecture with Real-Time Reconfigurability for DNN Acceleration
by: Chen, Xingzhen, et al.
Published: (2026)

Accelerating Multi-Scale Deformable Attention Using Near-Memory-Processing Architecture
by: Li, Huize, et al.
Published: (2026)