Image de couverture de livre

Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Jiaxi, Zhu, Yue, Lee, Eun Kyung, Nahrstedt, Klara
Format:	Preprint
Publié:	2025
Sujets:	Performance Artificial Intelligence Hardware Architecture Distributed, Parallel, and Cluster Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception
par: Odema, Mohanad, et autres
Publié: (2024)

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
par: Qin, Ruoyu, et autres
Publié: (2024)

COMET: Neural Cost Model Explanation Framework
par: Chaudhary, Isha, et autres
Publié: (2023)

GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model
par: Kumar, Deepak, et autres
Publié: (2025)

ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs
par: Lei, Jianlong, et autres
Publié: (2026)

Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
par: Vellaisamy, Prabhu, et autres
Publié: (2025)

Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers
par: Renney, Harri, et autres
Publié: (2026)

RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators
par: Tang, Xinsheng, et autres
Publié: (2026)

Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
par: Shi, Tianyao, et autres
Publié: (2025)

GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions
par: Shi, Tianyao, et autres
Publié: (2024)

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution
par: Panigrahy, Deepak, et autres
Publié: (2026)

Scaling Intelligence: Designing Data Centers for Next-Gen Language Models
par: Tithi, Jesmin Jahan, et autres
Publié: (2025)

Performance Analysis of HPC applications on the Aurora Supercomputer: Exploring the Impact of HBM-Enabled Intel Xeon Max CPUs
par: Ibeid, Huda, et autres
Publié: (2025)

Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML
par: John, Chelsea Maria, et autres
Publié: (2024)

SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators
par: Odema, Mohanad, et autres
Publié: (2024)

GigaAPI for GPU Parallelization
par: Suvarna, M., et autres
Publié: (2025)

UPMEM Unleashed: Software Secrets for Speed
par: Chmielewski, Krystian, et autres
Publié: (2025)

Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis
par: Luo, Weile, et autres
Publié: (2025)

Experimental Assessment of Containers Running on Top of Virtual Machines
par: Aqasizade, Hossein, et autres
Publié: (2024)

Compiler Support for Speculation in Decoupled Access/Execute Architectures
par: Szafarczyk, Robert, et autres
Publié: (2025)

Profiling Concurrent Vision Inference Workloads on NVIDIA Jetson -- Extended
par: Chakraborty, Abhinaba, et autres
Publié: (2025)

Exploring and Evaluating Real-world CXL: Use Cases and System Adoption
par: Wang, Xi, et autres
Publié: (2024)

Parallelizing a modern GPU simulator
par: Huerta, Rodrigo, et autres
Publié: (2025)

Can Asymmetric Tile Buffering Be Beneficial?
par: Wang, Chengyue, et autres
Publié: (2025)

Exploiting long vectors with a CFD code: a co-design show case
par: Blancafort, Marc, et autres
Publié: (2024)

Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs
par: Qararyah, Fareed, et autres
Publié: (2024)

Simopt -- Simulation pass for Speculative Optimisation of FPGA-CAD flow
par: Wadhwa, Eashan, et autres
Publié: (2024)

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
par: Fan, Ruibo, et autres
Publié: (2026)

Serving Large Language Models on Huawei CloudMatrix384
par: Zuo, Pengfei, et autres
Publié: (2025)

PRESERVE: Prefetching Model Weights and KV-Cache in Distributed LLM Serving
par: Yüzügüler, Ahmet Caner, et autres
Publié: (2025)

Wattlytics: A Web Platform for Co-Optimizing Performance, Energy, and TCO in HPC Clusters
par: Afzal, Ayesha, et autres
Publié: (2026)

DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs
par: Hu, Ziyu, et autres
Publié: (2025)

Flex-TPU: A Flexible TPU with Runtime Reconfigurable Dataflow Architecture
par: Elbtity, Mohammed, et autres
Publié: (2024)

DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency
par: Stojkovic, Jovan, et autres
Publié: (2024)

ZKProphet: Understanding Performance of Zero-Knowledge Proofs on GPUs
par: Verma, Tarunesh, et autres
Publié: (2025)

Vector-Centric Machine Learning Systems: A Cross-Stack Approach
par: Jiang, Wenqi
Publié: (2025)

HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures
par: Liu, Fangxin, et autres
Publié: (2026)

Design and Implementation of an IoT Cluster with Raspberry Pi Powered by Solar Energy: A Theoretical Approach
par: Portillo, Noel
Publié: (2025)

OPMOS: Ordered Parallel Algorithm for Multi-Objective Shortest-Paths
par: Gold, Leo, et autres
Publié: (2024)

Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving
par: Tian, Yuyang, et autres
Publié: (2025)