Cover Image

UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Weikai, Zeng, Wenxuan, Huang, Qianqian, Li, Meng, Huang, Ru
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

NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference
by: Xu, Weikai, et al.
Published: (2026)

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

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

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

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

3DGauCIM: Accelerating Static/Dynamic 3D Gaussian Splatting via Digital CIM for High Frame Rate Real-Time Edge Rendering
by: Huang, Wei-Hsing, et al.
Published: (2025)

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

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

RCW-CIM: A Digital CIM-based LLM Accelerator with Read-Compute/Write
by: Guo, Yan-Cheng, et al.
Published: (2026)

VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator
by: Wang, Zhican, et al.
Published: (2025)

Voxel-CIM: An Efficient Compute-in-Memory Accelerator for Voxel-based Point Cloud Neural Networks
by: Lin, Xipeng, et al.
Published: (2024)

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

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

Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading
by: Meng, William, et al.
Published: (2025)

EasyACIM: An End-to-End Automated Analog CIM with Synthesizable Architecture and Agile Design Space Exploration
by: Zhang, Haoyi, et al.
Published: (2024)

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

Be CIM or Be Memory: A Dual-mode-aware DNN Compiler for CIM Accelerators
by: Zhao, Shixin, et al.
Published: (2025)

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

CIMinus: Empowering Sparse DNN Workloads Modeling and Exploration on SRAM-based CIM Architectures
by: Qi, Yingjie, et al.
Published: (2025)

Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
by: Wu, Haoran, et al.
Published: (2025)

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

ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance
by: Xie, Tong, et al.
Published: (2025)

Ouroboros: Wafer-Scale SRAM CIM with Token-Grained Pipelining for Large Language Model Inference
by: Liu, Yiqi, et al.
Published: (2026)

EdgeMM: Multi-Core CPU with Heterogeneous AI-Extension and Activation-aware Weight Pruning for Multimodal LLMs at Edge
by: Bai, Kangbo, et al.
Published: (2025)

L3: DIMM-PIM Integrated Architecture and Coordination for Scalable Long-Context LLM Inference
by: Liu, Qingyuan, et al.
Published: (2025)

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

Acore-CIM: build accurate and reliable mixed-signal CIM cores with RISC-V controlled self-calibration
by: Numan, Omar, et al.
Published: (2025)

CIM-Tuner: Balancing the Compute and Storage Capacity of SRAM-CIM Accelerator via Hardware-mapping Co-exploration
by: Chen, Jinwu, et al.
Published: (2026)

ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs
by: Lei, Jianlong, 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)

Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits
by: Kim, Dowon, et al.
Published: (2025)

Leveraging Compute-in-Memory for Efficient Generative Model Inference in TPUs
by: Zhu, Zhantong, et al.
Published: (2025)

Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture
by: Feng, Yu, et al.
Published: (2024)

CIMFlow: An Integrated Framework for Systematic Design and Evaluation of Digital CIM Architectures
by: Qi, Yingjie, et al.
Published: (2025)

BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache
by: Du, Dayou, 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)

Adaptive Multi-Objective Tiered Storage Configuration for KV Cache in LLM Service
by: Zheng, Xianzhe, 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)

Efficient yet Accurate End-to-End SC Accelerator Design
by: Li, Meng, et al.
Published: (2024)

DCI: A Coordinated Allocation and Filling Workload-Aware Dual-Cache Allocation GNN Inference Acceleration System
by: Luo, Yi, et al.
Published: (2025)