Cover Image

AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Matsushima, Kosuke, Okoshi, Yasuyuki, Motomura, Masato, Fujiki, Daichi
Format:	Preprint
Published:	2026
Subjects:	Hardware Architecture Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Late Breaking Results: Quamba-SE: Soft-edge Quantizer for Activations in State Space Models
by: Chen, Yizhi, et al.
Published: (2026)

AIM: Software and Hardware Co-design for Architecture-level IR-drop Mitigation in High-performance PIM
by: Zhang, Yuanpeng, et al.
Published: (2025)

Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators
by: Kim, Jiyoon, et al.
Published: (2025)

PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs
by: Malekar, Jinendra, et al.
Published: (2025)

MEADOW: Memory-efficient Dataflow and Data Packing for Low Power Edge LLMs
by: Moitra, Abhishek, et al.
Published: (2025)

The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
by: Otsuka, Hikari, et al.
Published: (2025)

PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection
by: Park, Hyoseok, et al.
Published: (2026)

Improving Quantization with Post-Training Model Expansion
by: Franco, Giuseppe, et al.
Published: (2025)

PIMphony: Overcoming Bandwidth and Capacity Inefficiency in PIM-based Long-Context LLM Inference System
by: Kwon, Hyucksung, et al.
Published: (2024)

Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers
by: Lu, Jinming, et al.
Published: (2025)

On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
by: Huang, Wei, et al.
Published: (2023)

PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System
by: Rhyner, Steve, et al.
Published: (2024)

FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression
by: Qiao, Ye, et al.
Published: (2026)

MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
by: Zhang, Yu, et al.
Published: (2024)

Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
by: Abushahla, Hamza A., et al.
Published: (2025)

MEMHD: Memory-Efficient Multi-Centroid Hyperdimensional Computing for Fully-Utilized In-Memory Computing Architectures
by: Kang, Do Yeong, et al.
Published: (2025)

Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction
by: Chhugani, Jatin, et al.
Published: (2026)

RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks
by: Mohammadi, Ali Soltan, et al.
Published: (2026)

MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization
by: Ramachandran, Akshat, et al.
Published: (2024)

ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation System
by: Kim, Youngsuk, et al.
Published: (2024)

SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization
by: Xie, Rui, et al.
Published: (2024)

HH-PIM: Dynamic Optimization of Power and Performance with Heterogeneous-Hybrid PIM for Edge AI Devices
by: Jeon, Sangmin, et al.
Published: (2025)

Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns
by: Bambhaniya, Abhimanyu, et al.
Published: (2026)

Efficient Calibration for RRAM-based In-Memory Computing using DoRA
by: Dong, Weirong, et al.
Published: (2025)

HTM-EAR: Importance-Preserving Tiered Memory with Hybrid Routing under Saturation
by: Singh, Shubham Kumar
Published: (2026)

SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems
by: Gogineni, Kailash, et al.
Published: (2024)

Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format
by: Fang, Chao, et al.
Published: (2024)

TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
by: Kang, Hao, et al.
Published: (2024)

NeFT: Negative Feedback Training to Improve Robustness of Compute-In-Memory DNN Accelerators
by: Qin, Yifan, et al.
Published: (2023)

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
by: Zhou, Wenyong, et al.
Published: (2025)

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

AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technology
by: Cong, Rongqing, et al.
Published: (2024)

LP5X-PIM Sim: A High-Fidelity HW/SW Integrated Simulator for LPDDR5X-PIM
by: Cha, SangHoon, et al.
Published: (2026)

NeuroSim V1.5: Improved Software Backbone for Benchmarking Compute-in-Memory Accelerators with Device and Circuit-level Non-idealities
by: Read, James, et al.
Published: (2025)

Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing
by: Knunyants, Ivan, et al.
Published: (2025)

Sangam: Chiplet-Based DRAM-PIM Accelerator with CXL Integration for LLM Inferencing
by: Kiyawat, Khyati, et al.
Published: (2025)

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis
by: Bi, Zhen, et al.
Published: (2026)

SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs
by: AbouElhamayed, Ahmed F., et al.
Published: (2025)

eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization
by: Agrawal, Aditya, et al.
Published: (2024)

A Unified Memory Perspective for Probabilistic Trustworthy AI
by: Zhao, Xueji, et al.
Published: (2026)