activity
20242026
collaborators

6 papers

cs.AR2026

MoE Expert Execution in Disaggregated LLM Serving with a High-Bandwidth ReRAM Near-Memory Architecture

Kunming Shao, Ming Zeng, Xin Yuan +5

Attention-FFN disaggregation maps LLM modules to specialized pools, creating an opening to keep Mixture-of-Experts (MoE) weights resident in a high-bandwidth FFN pool. Decode SLOs,…

cs.AR2026

Balancing FP8 Computation Accuracy and Efficiency on Digital CIM via Shift-Aware On-the-fly Aligned-Mantissa Bitwidth Prediction

Liang Zhao, Kunming Shao, Zhipeng Liao +4

FP8 low-precision formats have gained significant adoption in Transformer inference and training. However, existing digital compute-in-memory (DCIM) architectures face challenges i…

cs.AR2026

DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models

Kunming Shao, Liang Zhao, Jiangnan Yu +5

Stochastic computing (SC) offers hardware simplicity but suffers from low throughput, while high-throughput Digital Computing-in-Memory (DCIM) is bottlenecked by costly adder logic…

cs.AR2025

DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation

Kunming Shao, Zhipeng Liao, Jiangnan Yu +9

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval but faces challenges on edge devices due to high storage, ene…

cs.AR2025

A Flexible Precision Scaling Deep Neural Network Accelerator with Efficient Weight Combination

Liang Zhao, Kunming Shao, Fengshi Tian +3

Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is…

cs.AR2024

SynDCIM: A Performance-Aware Digital Computing-in-Memory Compiler with Multi-Spec-Oriented Subcircuit Synthesis

Kunming Shao, Fengshi Tian, Xiaomeng Wang +12

Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI…