Cover Image

SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Hengrui, Patel, Pratyush, Ning, August, Wentzlaff, David
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DUET: Disaggregated Hybrid Mamba-Transformer LLMs with Prefill and Decode-Specific Packages
by: Kanani, Alish, et al.
Published: (2026)

Tascade: Hardware Support for Atomic-free, Asynchronous and Efficient Reduction Trees
by: Orenes-Vera, Marcelo, et al.
Published: (2023)

Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving
by: Ding, Jianru, et al.
Published: (2026)

DCRA: A Distributed Chiplet-based Reconfigurable Architecture for Irregular Applications
by: Orenes-Vera, Marcelo, et al.
Published: (2023)

Muchisim: A Simulation Framework for Design Exploration of Multi-Chip Manycore Systems
by: Orenes-Vera, Marcelo, et al.
Published: (2023)

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
by: Fan, Ruibo, et al.
Published: (2026)

Integrated Hardware Architecture and Device Placement Search
by: Wang, Irene, et al.
Published: (2024)

A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware
by: Zhang, Shichang, et al.
Published: (2023)

GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions
by: Shi, Tianyao, et al.
Published: (2024)

Efficient, VRAM-Constrained xLM Inference on Clients
by: Ukarande, Aditya, et al.
Published: (2026)

The Dawn of Disaggregation and the Coherence Conundrum: A Call for Federated Coherence
by: Hong, Jaewan, et al.
Published: (2025)

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs
by: Yang, Jinwu, et al.
Published: (2026)

Performance Modeling and Workload Analysis of Distributed Large Language Model Training and Inference
by: Kundu, Joyjit, et al.
Published: (2024)

Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization
by: Chen, Hao Mark, et al.
Published: (2025)

An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC
by: Jobst, Matthias, et al.
Published: (2025)

Survey of Disaggregated Memory: Cross-layer Technique Insights for Next-Generation Datacenters
by: Wang, Jing, et al.
Published: (2025)

Detecting Anomalies in Machine Learning Infrastructure via Hardware Telemetry
by: Chen, Ziji, et al.
Published: (2025)

Analyzing a Two-Tier Disaggregated Memory Protection Scheme Based on Memory Replication
by: Volos, Haris, et al.
Published: (2025)

PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers
by: Yeo, Gwangoo, et al.
Published: (2024)

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
by: Qin, Ruoyu, et al.
Published: (2024)

Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading
by: Meng, William, et al.
Published: (2025)

Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference
by: Chung, Euijun, et al.
Published: (2026)

HgPCN: A Heterogeneous Architecture for E2E Embedded Point Cloud Inference
by: Gao, Yiming, et al.
Published: (2025)

MLDSE: Scaling Design Space Exploration Infrastructure for Multi-Level Hardware
by: Qu, Huanyu, et al.
Published: (2025)

A Heterogeneous Chiplet Architecture for Accelerating End-to-End Transformer Models
by: Sharma, Harsh, et al.
Published: (2023)

Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel
by: Liu, Yiqi, et al.
Published: (2026)

MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems
by: Hsia, Samuel, et al.
Published: (2023)

MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
by: Bambhaniya, Abhimanyu Rajeshkumar, et al.
Published: (2025)

SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
by: Kakolyris, Andreas Kosmas, et al.
Published: (2024)

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
by: Bambhaniya, Abhimanyu, et al.
Published: (2024)

Llumnix: Dynamic Scheduling for Large Language Model Serving
by: Sun, Biao, et al.
Published: (2024)

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
by: Li, Mufei, et al.
Published: (2024)

CCSS: Hardware-Accelerated RTL Simulation with Fast Combinational Logic Computing and Sequential Logic Synchronization
by: Feng, Weigang, et al.
Published: (2025)

A High Energy-Efficiency Multi-core Neuromorphic Architecture for Deep SNN Training
by: Li, Mingjing, et al.
Published: (2024)

MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI
by: Tschand, Arya, et al.
Published: (2024)

Workload-Aware Hardware Accelerator Mining for Distributed Deep Learning Training
by: Adnan, Muhammad, et al.
Published: (2024)

Switchboard: An Open-Source Framework for Modular Simulation of Large Hardware Systems
by: Herbst, Steven, et al.
Published: (2024)

MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
by: Zhou, Zhuoshan, et al.
Published: (2026)

MemPool Flavors: Between Versatility and Specialization in a RISC-V Manycore Cluster
by: Mazzola, Sergio, et al.
Published: (2025)

Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference
by: Yu, Zhongkai, et al.
Published: (2025)