Cover Image

VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhican, Fan, Hongxiang, Waris, Haroon, Wang, Gang, Li, Zhenyu, Jiang, Jianfei, Sun, Yanan, He, Guanghui
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
by: Wang, Zhican, et al.
Published: (2025)

DEFA: Efficient Deformable Attention Acceleration via Pruning-Assisted Grid-Sampling and Multi-Scale Parallel Processing
by: Xu, Yansong, et al.
Published: (2024)

HillInfer: Efficient Long-Context LLM Inference on the Edge with Hierarchical KV Eviction using SmartSSD
by: Sun, He, et al.
Published: (2026)

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

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

SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
by: Wu, Junyi, et al.
Published: (2025)

BackCache: Mitigating Contention-Based Cache Timing Attacks by Hiding Cache Line Evictions
by: Wang, Quancheng, et al.
Published: (2023)

MIREDO: MIP-Driven Resource-Efficient Dataflow Optimization for Computing-in-Memory Accelerator
by: He, Xiaolin, et al.
Published: (2025)

A High-Throughput FPGA Accelerator for Lightweight CNNs With Balanced Dataflow
by: Zhao, Zhiyuan, et al.
Published: (2024)

Multilayer Dataflow: Orchestrate Butterfly Sparsity to Accelerate Attention Computation
by: Wu, Haibin, et al.
Published: (2024)

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
by: Fang, Yunhua, et al.
Published: (2025)

LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization
by: He, Siyuan, et al.
Published: (2025)

Stream-HLS: Towards Automatic Dataflow Acceleration
by: Basalama, Suhail, et al.
Published: (2025)

VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
by: Yao, Jiayi, et al.
Published: (2026)

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
by: Chang, Kaiyan, et al.
Published: (2025)

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

A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling Formats
by: Cheng, Jianyi, et al.
Published: (2023)

AccelCIM: Systematic Dataflow Exploration for SRAM Compute-in-Memory Accelerator
by: Xue, Chenhao, et al.
Published: (2026)

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

Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization
by: Kim, Minsu, et al.
Published: (2025)

Harmonia: Algorithm-Hardware Co-Design for Memory- and Compute-Efficient BFP-based LLM Inference
by: Wang, Xinyu, et al.
Published: (2026)

UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference
by: Xu, Weikai, et al.
Published: (2025)

PC2IM: An Efficient In-Memory Computing Accelerator for 3D Point Cloud
by: Wang, Dengfeng, et al.
Published: (2026)

StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs
by: Ye, Hanchen, et al.
Published: (2025)

Comparative Characterization of KV Cache Management Strategies for LLM Inference
by: Mamo, Oteo, et al.
Published: (2026)

Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing
by: Xia, Tianhua, et al.
Published: (2025)

LoopTree: Exploring the Fused-layer Dataflow Accelerator Design Space
by: Gilbert, Michael, et al.
Published: (2024)

DataMaestro: A Versatile and Efficient Data Streaming Engine Bringing Decoupled Memory Access To Dataflow Accelerators
by: Yi, Xiaoling, et al.
Published: (2025)

StreamDCIM: A Tile-based Streaming Digital CIM Accelerator with Mixed-stationary Cross-forwarding Dataflow for Multimodal Transformer
by: Qin, Shantian, et al.
Published: (2025)

Accelerating 3D Gaussian Splatting with Neural Sorting and Axis-Oriented Rasterization
by: Wang, Zhican, et al.
Published: (2025)

Stream: Design Space Exploration of Layer-Fused DNNs on Heterogeneous Dataflow Accelerators
by: Symons, Arne, et al.
Published: (2022)

LEAP: LLM Inference on Scalable PIM-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism
by: Wang, Yimin, et al.
Published: (2025)

DS2SC-Agent: A Multi-Agent Automated Pipeline for Rapid Chiplet Model Generation
by: Wu, Yiwei, et al.
Published: (2026)

FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Efficient Multi-Head Attention on Tile-Based Many-PE Accelerators
by: Zhang, Chi, et al.
Published: (2025)

Sparsity-Aware Streaming SNN Accelerator with Output-Channel Dataflow for Automatic Modulation Classification
by: Yang, Kuilian, et al.
Published: (2026)

SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators
by: Umuroglu, Yaman, et al.
Published: (2025)

Fast Cross-Operator Optimization of Attention Dataflow
by: Chang, Haodong, et al.
Published: (2026)

CODO: An Automated Compiler for Comprehensive Dataflow Optimization
by: Zhang, Weichuang, et al.
Published: (2026)

FEATHER: A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching
by: Tong, Jianming, et al.
Published: (2024)

Adaptive KV Cache Reuse for Fast Long-Context LLM Serving
by: li, Fei, et al.
Published: (2026)