LaMoSys3.5D: Enabling 3.5D-IC-Based Large Language Model Inference Serving Systems via Hardware/Software Co-Design
Fuente:
arXiv
Guardado en:
| Autores principales: | Wang, Qipan, Zhang, Zhe, Li, Shuangchen, Zheng, Hongzhong, Liang, Zheng, Lin, Yibo, Wang, Runsheng, Huang, Ru |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
ATSim3.5D: A Multiscale Thermal Simulator for 3.5D-IC Systems based on Nonlinear Multigrid Method
por: Wang, Qipan, et al.
Publicado: (2026)
por: Wang, Qipan, et al.
Publicado: (2026)
MORE-Stress: Model Order Reduction based Efficient Numerical Algorithm for Thermal Stress Simulation of TSV Arrays in 2.5D/3D IC
por: Zhu, Tianxiang, et al.
Publicado: (2024)
por: Zhu, Tianxiang, et al.
Publicado: (2024)
ATSim3D: Towards Accurate Thermal Simulator for Heterogeneous 3D-IC Systems Considering Nonlinear Leakage and Conductivity
por: Wang, Qipan, et al.
Publicado: (2026)
por: Wang, Qipan, et al.
Publicado: (2026)
ATMPlace: Analytical Thermo-Mechanical-Aware Placement Framework for 2.5D-IC
por: Wang, Qipan, et al.
Publicado: (2025)
por: Wang, Qipan, et al.
Publicado: (2025)
HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing
por: Huang, Haochen, et al.
Publicado: (2025)
por: Huang, Haochen, et al.
Publicado: (2025)
Hardware-Software Co-design for 3D-DRAM-based LLM Serving Accelerator
por: Li, Cong, et al.
Publicado: (2026)
por: Li, Cong, et al.
Publicado: (2026)
D3.5 Pilot sites energy
por: Pitz, Manuel
Publicado: (2024)
por: Pitz, Manuel
Publicado: (2024)
Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving
por: Pan, Yue, et al.
Publicado: (2025)
por: Pan, Yue, et al.
Publicado: (2025)
AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
por: Zhong, Shuzhang, et al.
Publicado: (2024)
por: Zhong, Shuzhang, et al.
Publicado: (2024)
D3.5 Smart Tags v1
por: DigInTraCE project
Publicado: (2025)
por: DigInTraCE project
Publicado: (2025)
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
por: Zhong, Shuzhang, et al.
Publicado: (2025)
por: Zhong, Shuzhang, et al.
Publicado: (2025)
Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
por: Luo, Shuqing, et al.
Publicado: (2026)
por: Luo, Shuqing, et al.
Publicado: (2026)
Fairclimate_D3.5 Research model and survey instrument
por: University of Liège
Publicado: (2025)
por: University of Liège
Publicado: (2025)
Leveraging 3D Technologies for Hardware Security: Opportunities and Challenges
por: Gu, Peng, et al.
Publicado: (2025)
por: Gu, Peng, et al.
Publicado: (2025)
METRO: A Software-Hardware Co-Design of Interconnections for Spatial DNN Accelerators
por: Wang, Zhao, et al.
Publicado: (2021)
por: Wang, Zhao, et al.
Publicado: (2021)
D3.5 Report on impact logistics outsourcing on employment - Executive Summary
por: Reschape Consortium
Publicado: (2025)
por: Reschape Consortium
Publicado: (2025)
SecIC3: Customizing IC3 for Hardware Security Verification
por: Tan, Qinhan, et al.
Publicado: (2026)
por: Tan, Qinhan, et al.
Publicado: (2026)
Study on the Forming Process and Microstructural Formation Mechanism of Wire and Arc Additive Manufacturing Ti‐6.5Al‐3.5Mo‐1.5Zr‐0.3Si Titanium Alloy
por: Kaikui Zheng, et al.
Publicado: (2026)
por: Kaikui Zheng, et al.
Publicado: (2026)
SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
por: Bandyopadhyay, Hmrishav, et al.
Publicado: (2025)
por: Bandyopadhyay, Hmrishav, et al.
Publicado: (2025)
Emu3.5: Native Multimodal Models are World Learners
por: Cui, Yufeng, et al.
Publicado: (2025)
por: Cui, Yufeng, et al.
Publicado: (2025)
CogSys: Efficient and Scalable Neurosymbolic Cognition System via Algorithm-Hardware Co-Design
por: Wan, Zishen, et al.
Publicado: (2025)
por: Wan, Zishen, et al.
Publicado: (2025)
FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs
por: Xie, Xilong, et al.
Publicado: (2025)
por: Xie, Xilong, et al.
Publicado: (2025)
Qwen3.5-Omni Technical Report
por: Qwen Team
Publicado: (2026)
por: Qwen Team
Publicado: (2026)
GPT-3.5 for Grammatical Error Correction
por: Katinskaia, Anisia, et al.
Publicado: (2024)
por: Katinskaia, Anisia, et al.
Publicado: (2024)
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
por: Xu, Haiyang, et al.
Publicado: (2026)
por: Xu, Haiyang, et al.
Publicado: (2026)
The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
por: Hu, Siyuan, et al.
Publicado: (2024)
por: Hu, Siyuan, et al.
Publicado: (2024)
Structures, photoluminescence, and magnetism of 1D lanthanide coordination polymers dominated on 3,5‐dichlorobenzoate
por: Yanping Dong, et al.
Publicado: (2024)
por: Yanping Dong, et al.
Publicado: (2024)
MERE: Hardware-Software Co-Design for Masking Cache Miss Latency in Embedded Processors
por: You, Dean, et al.
Publicado: (2025)
por: You, Dean, et al.
Publicado: (2025)
Hardware-Software Co-Design for Accelerating Transformer Inference Leveraging Compute-in-Memory
por: Kim, Dong Eun, et al.
Publicado: (2025)
por: Kim, Dong Eun, et al.
Publicado: (2025)
ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving
por: Go, Seokjin, et al.
Publicado: (2026)
por: Go, Seokjin, et al.
Publicado: (2026)
The rIC3 Hardware Model Checker
por: Su, Yuheng, et al.
Publicado: (2025)
por: Su, Yuheng, et al.
Publicado: (2025)
A 3D Chemodynamical Census of Inner-Galaxy Metal-poor Giants to [Fe/H]~-3.5
por: Sun, Shenglan, et al.
Publicado: (2025)
por: Sun, Shenglan, et al.
Publicado: (2025)
The planar Turan number of double star S_(3,5)
por: Liu, Dandan, et al.
Publicado: (2025)
por: Liu, Dandan, et al.
Publicado: (2025)
NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering
por: Zhou, Zhe, et al.
Publicado: (2024)
por: Zhou, Zhe, et al.
Publicado: (2024)
P‐3.5: Research on Reducing Moiré Patterns in Naked‐eye 3D Displays through Optimizing Lenticular Lens Tilt Angle
por: Yuan Gao, et al.
Publicado: (2024)
por: Yuan Gao, et al.
Publicado: (2024)
Optimal additive quaternary codes of dimension $3.5$ and $4$
por: Kurz, Sascha
Publicado: (2024)
por: Kurz, Sascha
Publicado: (2024)
Can GPT-3.5 Generate and Code Discharge Summaries?
por: Falis, Matúš, et al.
Publicado: (2024)
por: Falis, Matúš, et al.
Publicado: (2024)
Table 3.5 Content and composition of air in fresh ice
por: Stauffer, Bernhard
Publicado: (1981)
por: Stauffer, Bernhard
Publicado: (1981)
Tropical SSTs over the past 3.5 million years
por: Herbert, Timothy D, et al.
Publicado: (2017)
por: Herbert, Timothy D, et al.
Publicado: (2017)
AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design
por: Liang, Yanbiao, et al.
Publicado: (2025)
por: Liang, Yanbiao, et al.
Publicado: (2025)
Ejemplares similares
-
ATSim3.5D: A Multiscale Thermal Simulator for 3.5D-IC Systems based on Nonlinear Multigrid Method
por: Wang, Qipan, et al.
Publicado: (2026) -
MORE-Stress: Model Order Reduction based Efficient Numerical Algorithm for Thermal Stress Simulation of TSV Arrays in 2.5D/3D IC
por: Zhu, Tianxiang, et al.
Publicado: (2024) -
ATSim3D: Towards Accurate Thermal Simulator for Heterogeneous 3D-IC Systems Considering Nonlinear Leakage and Conductivity
por: Wang, Qipan, et al.
Publicado: (2026) -
ATMPlace: Analytical Thermo-Mechanical-Aware Placement Framework for 2.5D-IC
por: Wang, Qipan, et al.
Publicado: (2025) -
HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing
por: Huang, Haochen, et al.
Publicado: (2025)