Accelerating Retrieval Augmented Language Model via PIM and PNM Integration
Open Access
- 17 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 246-262
Abstract
No abstract availableFunding Information
- Institute of Information & Communications Technology Planning & Evaluation (2022-0-00441, RS-2020-II201361, RS-2025-02304183)
- National Research Foundation of Korea (2022R1A4A1032361, RS-2025-00560614)
- IC Design Education Center
This publication has 65 references indexed in Scilit:
- Thermal characterization methodology for thin bond-line interfaces with high conductive materialsThermal Science and Engineering Progress, 2024
- An LPDDR-based CXL-PNM Platform for TCO-efficient Inference of Transformer-based Large Language Models2024
- Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology2024
- Thermal conductivity of group IV elemental semiconductorsJournal of Applied Physics, 2023
- DIMM-Link: Enabling Efficient Inter-DIMM Communication for Near-Memory Processing2023
- RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing2020
- The true Processing In Memory accelerator2019
- Design of Processing-“Inside”-Memory Optimized for DRAM BehaviorsIEEE Access, 2019
- Ultra-thin chips for high-performance flexible electronicsnpj Flexible Electronics, 2018
- ASAP7: A 7-nm finFET predictive process design kitMicroelectronics Journal, 2016