A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs
Open Access
- 22 March 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 5-24
Abstract
No abstract availableAll Related Versions
Funding Information
- National Research Foundation of Korea (NRF) (2022R1C1C1011307)
- National Research Foundation of Korea (NRF) (RS-2025-00519994)
- Institute of Information communications Technology Planning Evaluation (IITP) (RS-2024-00395134)
- Institute of Information communications Technology Planning Evaluation (IITP) (RS-2024-00347394)
- Institute of Information communications Technology Planning Evaluation (IITP) (RS-2023-00256081)
- Institute of Information communications Technology Planning Evaluation (IITP) (RS-2021-II211343)
- Institute of Information communications Technology Planning Evaluation (IITP) (RS-2024-00459026)
- Samsung Memory Research Center (SMRC) (None)
- Korea Basic Science Institute (National research Facilities and Equipment Center) (RS-2025-00564840)
This publication has 21 references indexed in Scilit:
- Efficient Tensor Offloading for Large Deep-Learning Model Training based on Compute Express Link2024
- MegIS: High-Performance, Energy-Efficient, and Low-Cost Metagenomic Analysis with In-Storage Processing2024
- Splitwise: Efficient Generative LLM Inference Using Phase Splitting2024
- Memory Pooling With CXLIEEE Micro, 2023
- DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation2022
- Nvidia Hopper GPU and Grace CPU HighlightsComputing in Science & Engineering, 2022
- Biscuit: A Framework for Near-Data Processing of Big Data Workloads2016
- A Low Power 64 Gb MLC NAND-Flash Memory in 15 nm CMOS TechnologyIEEE Journal of Solid-State Circuits, 2015
- Active disks for large-scale data processingComputer, 2001
- A case for intelligent disks (IDISKs)ACM SIGMOD Record, 1998