Cover Image

PIM-SHERPA: Software Method for On-device LLM Inference by Resolving PIM Memory Attribute and Layout Inconsistencies

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Sunjung, Cha, Sanghoon, Kim, Hyeonsu, Seo, Seungwoo, Ro, Yuhwan, Lee, Sukhan, Kim, Byeongho, Park, Yongjun, Sohn, Kyomin, Lee, Seungwon, Yu, Jaehoon
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

PIMutation: Exploring the Potential of PIM Architecture for Quantum Circuit Simulation
by: Lee, Dongin, et al.
Published: (2025)

Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology
by: Hyun, Bongjoon, et al.
Published: (2023)

PIM-MMU: A Memory Management Unit for Accelerating Data Transfers in Commercial PIM Systems
by: Lee, Dongjae, et al.
Published: (2024)

ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation System
by: Kim, Youngsuk, 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)

AME-PIM: Can Memory be Your Next Tensor Accelerator?
by: Venieri, Emanuele, et al.
Published: (2026)

Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching
by: Yun, Sungmin, et al.
Published: (2024)

PIM-malloc: A Fast and Scalable Dynamic Memory Allocator for Processing-In-Memory (PIM) Architectures
by: Lee, Dongjae, et al.
Published: (2025)

IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System
by: Seo, Minseok, et al.
Published: (2024)

Inclusive-PIM: Hardware-Software Co-design for Broad Acceleration on Commercial PIM Architectures
by: Alsop, Johnathan, et al.
Published: (2023)

PIM or CXL-PIM? Understanding Architectural Trade-offs Through Large-Scale Benchmarking
by: Lee, I-Ting, et al.
Published: (2025)

NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
by: Heo, Guseul, et al.
Published: (2024)

LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM
by: Hong, Junguk, et al.
Published: (2026)

FEATHer: Fourier-Efficient Adaptive Temporal Hierarchy Forecaster for Time-Series Forecasting
by: Lee, Jaehoon, et al.
Published: (2026)

Per-Row Activation Counting on Real Hardware: Demystifying Performance Overheads
by: Kim, Jumin, et al.
Published: (2025)

Treatment Intensity of Speech Intervention via Telepractice for Children with Speech Sound Disorders: A Systematic Review. EBP Briefs. Volume 15, Issue 3
by: Thao, Sunjung Kim, et al.
Published: (2022)

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

Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models
by: Kim, Jungwoo, et al.
Published: (2026)

Graphene Oxide and its Composites: Advanced Membranes for Selective Water Permeation
by: Byeongho Lee, et al.
Published: (2024)

Annotated PIM Bibliography
by: Kogge, Peter M.
Published: (2026)

d18O composite records of of stalagmites PIM4 and PIM5
by: Della Libera, Marcela Eduarda, et al.
Published: (2022)

PIM-STM: Software Transactional Memory for Processing-In-Memory Systems
by: Lopes, André, et al.
Published: (2024)

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

UMDAM: A Unified Data Layout and DRAM Address Mapping for Heterogenous NPU-PIM
by: Huang, Hai
Published: (2025)

In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners
by: Kim, Jaehoon, et al.
Published: (2025)

Magnetic-field dependent VB- spin decoherence in hexagonal boron nitrides: A first-principles study
by: Lee, Jaewook, et al.
Published: (2025)

Magnetic‐Field Dependent V B − Spin Decoherence in Hexagonal Boron Nitrides: A First‐Principles Study
by: Jaewook Lee, et al.
Published: (2025)

Type-I Blowup Solutions for Yang-Mills Flow
by: Kim, Jaehwan, et al.
Published: (2024)

Dissecting and Re-architecting 3D NAND Flash PIM Arrays for Efficient Single-Batch Token Generation in LLMs
by: Jang, Yongjoo, et al.
Published: (2025)

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
by: Seo, Junyoung, et al.
Published: (2023)

Dense triangle-free $(n, d, λ)$-graphs for all orders
by: Kim, Jaehoon, et al.
Published: (2024)

OPSD Compresses What RLVR Teaches: A Post-RL Compaction Stage for Reasoning Models
by: Kim, Jaehoon, et al.
Published: (2026)

Non-split, alternating links bound unique Seifert surfaces in the 4-ball
by: Kim, Seungwon, et al.
Published: (2024)

THE PHASE-INVERSION MODEL (PIM) OF LOCALIZED COSMOLOGY
by: Osama, Ibrahim
Published: (2026)

Stable isotope records of stalagmite PIM4
by: Della Libera, Marcela Eduarda, et al.
Published: (2022)

Stable isotope records of stalagmite PIM5
by: Della Libera, Marcela Eduarda, et al.
Published: (2022)

U/Th ages of stalagmite PIM4
by: Della Libera, Marcela Eduarda, et al.
Published: (2022)

U/Th ages of stalagmite PIM5
by: Della Libera, Marcela Eduarda, et al.
Published: (2022)

PIM-FW: Hardware-Software Co-Design of All-pairs Shortest Paths in DRAM
by: Lu, Tsung-Han, et al.
Published: (2025)