Cover Image

Position: LLM Inference Should Be Evaluated as Energy-to-Token Production

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xiang, Yuan, Shimiao, Tang, Zhenheng, Dong, Peijie, Zhao, Kaiyong, Wang, Qiang, Li, Bo, Chu, Xiaowen
Format:	Preprint
Published:	2026
Subjects:	Computational Engineering, Finance, and Science Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DreamDDP: Accelerating Data Parallel Distributed LLM Training with Layer-wise Scheduled Partial Synchronization
by: Tang, Zhenheng, et al.
Published: (2025)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
by: Pan, Xinglin, et al.
Published: (2025)

FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression
by: Tang, Zhenheng, et al.
Published: (2024)

Argus: Token Aware Distributed LLM Inference Optimization
by: Wu, Panlong, et al.
Published: (2025)

BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems
by: Wang, Yuxin, et al.
Published: (2024)

FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
by: Tang, Zhenheng, et al.
Published: (2024)

Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
by: Tang, Zichen, et al.
Published: (2024)

A Cloud-based Real-time Probabilistic Remaining Useful Life (RUL) Estimation using the Sequential Monte Carlo (SMC) Method
by: Lyathakula, Karthik Reddy, et al.
Published: (2024)

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems
by: Wilkins, Grant, et al.
Published: (2024)

Decentralized LLM Inference over Edge Networks with Energy Harvesting
by: Khoshsirat, Aria, et al.
Published: (2024)

FedImpro: Measuring and Improving Client Update in Federated Learning
by: Tang, Zhenheng, et al.
Published: (2024)

DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance
by: Zhang, Yuning, et al.
Published: (2025)

Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations
by: Özcan, Miray, et al.
Published: (2025)

A GPU-boosted high-performance multi-working condition joint analysis framework for predicting dynamics of textured axial piston pump
by: Yao, Xin, et al.
Published: (2025)

Fault-Tolerant Hybrid-Parallel Training at Scale with Reliable and Efficient In-memory Checkpointing
by: Wang, Yuxin, et al.
Published: (2023)

ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training
by: Lin, Wenxiang, et al.
Published: (2026)

Towards Resource-Efficient Serverless LLM Inference with SLINFER
by: Xu, Chuhao, et al.
Published: (2025)

Characterizing GPU Energy Usage in Exascale-Ready Portable Science Applications
by: Godoy, William F., et al.
Published: (2025)

ElasWave: An Elastic-Native System for Scalable Hybrid-Parallel Training
by: Kang, Xueze, et al.
Published: (2025)

TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity
by: Lai, Ruiqi, et al.
Published: (2025)

LIME:Accelerating Collaborative Lossless LLM Inference on Memory-Constrained Edge Devices
by: Sun, Mingyu, et al.
Published: (2025)

TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
by: Bian, Zhuohang, et al.
Published: (2026)

HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
by: Dong, Jiangwen, et al.
Published: (2025)

Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference Architecture
by: Wu, Yu, et al.
Published: (2025)

Parallax: Efficient LLM Inference Service over Decentralized Environment
by: Tong, Chris, et al.
Published: (2025)

Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization
by: Chen, Jiu, et al.
Published: (2026)

Reduced and mixed precision turbulent flow simulations using explicit finite difference schemes
by: Siklósi, Bálint, et al.
Published: (2025)

In-Memory Non-Binary LDPC Decoding
by: Ferraz, Oscar, et al.
Published: (2025)

A parallel implementation of reduced-order modeling of large-scale systems
by: Farcas, Ionut-Gabriel, et al.
Published: (2025)

Reclaiming Idle CPU Cycles on Kubernetes: Sparse-Domain Multiplexing for Concurrent MPI-CFD Simulations
by: Xie, Tianfang
Published: (2026)

Making Tax Smart: Feasibility of Distributed Ledger Technology for building tax compliance functionality to Central Bank Digital Currency
by: Louvieris, Panos, et al.
Published: (2024)

GPU-accelerated Linear Algebra for Coupled Solvers in Industrial CFD Applications with OpenFOAM
by: Oliani, Stefano, et al.
Published: (2024)

Matrix-Free 3D SIMP Topology Optimization with Fused Gather-GEMM-Scatter Kernels
by: Yang, Shaoliang, et al.
Published: (2026)

Optimizing the Weather Research and Forecasting Model with OpenMP Offload and Codee
by: Chayanon, et al.
Published: (2024)

Mass Matrix Assembly on Tensor Cores for Implicit Particle-In-Cell Methods
by: Pennati, Luca, et al.
Published: (2026)

A GPU-based Compressible Combustion Solver for Applications Exhibiting Disparate Space and Time Scales
by: Carreon, Anthony, et al.
Published: (2025)

Level set-based inverse homogenisation of three-dimensional piezoelectric materials
by: Wegert, Zachary J., et al.
Published: (2024)

Intertemporal Pricing of Time-Bound Stablecoins: Measuring and Controlling the Liquidity-of-Time Premium
by: Borjigin, Ailiya, et al.
Published: (2025)

A Portable Multi-GPU Solver for Collisional Plasmas with Coulombic Interactions
by: Almgren-Bell, James, et al.
Published: (2025)

Smoothed aggregation algebraic multigrid for problems with heterogeneous and anisotropic materials
by: Firmbach, Max, et al.
Published: (2026)