Imagen de Portada

Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Youpeng, LV, Jinpeng, Wu, Di, Wang, Jun, Gooley, Christopher
Formato:	Preprint
Publicado:	2025
Materias:	Performance Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching
por: Zhao, Youpeng, et al.
Publicado: (2024)

ALISE: Accelerating Large Language Model Serving with Speculative Scheduling
por: Zhao, Youpeng, et al.
Publicado: (2024)

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving
por: Jayakody, Shakya, et al.
Publicado: (2026)

Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs
por: Liu, Yi
Publicado: (2026)

The Race to Efficiency: A New Perspective on AI Scaling Laws
por: Lu, Chien-Ping
Publicado: (2025)

Generalizing Scaling Laws for Dense and Sparse Large Language Models
por: Hossain, Md Arafat, et al.
Publicado: (2025)

AI-driven Java Performance Testing: Balancing Result Quality with Testing Time
por: Traini, Luca, et al.
Publicado: (2024)

Throughput Optimization as a Strategic Lever in Large-Scale AI Systems: Evidence from Dataloader and Memory Profiling Innovations
por: Jha, Mayank
Publicado: (2026)

Adaptive Orchestration for Large-Scale Inference on Heterogeneous Accelerator Systems Balancing Cost, Performance, and Resilience
por: Biran, Yahav, et al.
Publicado: (2025)

DeepContext: A Context-aware, Cross-platform, and Cross-framework Tool for Performance Profiling and Analysis of Deep Learning Workloads
por: Zhao, Qidong, et al.
Publicado: (2024)

Comment on paper: Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
por: Min, Yimeng
Publicado: (2024)

Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI
por: Atinafu, Yonas, et al.
Publicado: (2026)

Offloading and Quality Control for AI Generated Content Services in 6G Mobile Edge Computing Networks
por: Wang, Yitong, et al.
Publicado: (2023)

Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations
por: Rani, Pooja, et al.
Publicado: (2025)

TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
por: Liu, Xiaoxuan, et al.
Publicado: (2024)

LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics
por: Liu, Jiashuo, et al.
Publicado: (2025)

A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search
por: Ellis-Mohr, Austin R., et al.
Publicado: (2025)

Root Cause Localization for Microservice Systems in Cloud-edge Collaborative Environments
por: Zhu, Yuhan, et al.
Publicado: (2024)

Rapid Augmentations for Time Series (RATS): A High-Performance Library for Time Series Augmentation
por: Skaf, Wadie, et al.
Publicado: (2026)

Quantifying the Generalization Gap in Seizure Detection: A Large-Scale Empirical Benchmark via the SzCORE Challenge
por: Dan, Jonathan, et al.
Publicado: (2025)

XTC, A Research Platform for Optimizing AI Workload Operators
por: Hugo, Pompougnac, et al.
Publicado: (2025)

DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
por: Hu, Jinwei, et al.
Publicado: (2026)

LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs
por: Cai, Yanan, et al.
Publicado: (2025)

Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems
por: Zhao, Yushang, et al.
Publicado: (2025)

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
por: Fang, Yunhua, et al.
Publicado: (2025)

FlashOmni: A Unified Sparse Attention Engine for Diffusion Transformers
por: Qiao, Liang, et al.
Publicado: (2025)

Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles
por: Gallici, Matteo, et al.
Publicado: (2025)

Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification
por: Kermani, Arshia, et al.
Publicado: (2025)

A 4D Hybrid Algorithm to Scale Parallel Training to Thousands of GPUs
por: Singh, Siddharth, et al.
Publicado: (2023)

Energy Concerns with HPC Systems and Applications
por: Nana, Roblex, et al.
Publicado: (2023)

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta
por: Liao, Gang, et al.
Publicado: (2025)

This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs
por: Krupp, Lars, et al.
Publicado: (2026)

On the Compression of Language Models for Code: An Empirical Study on CodeBERT
por: d'Aloisio, Giordano, et al.
Publicado: (2024)

Impact of Data-Oriented and Object-Oriented Design on Performance and Cache Utilization with Artificial Intelligence Algorithms in Multi-Threaded CPUs
por: Arantes, Gabriel M., et al.
Publicado: (2025)

PerfDojo: Automated ML Library Generation for Heterogeneous Architectures
por: Ivanov, Andrei, et al.
Publicado: (2025)

Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends
por: Prieto, Pablo, et al.
Publicado: (2025)

PixLift: Accelerating Web Browsing via AI Upscaling
por: Atinafu, Yonas, et al.
Publicado: (2025)

Tiny-QMoE
por: Cashman, Jack, et al.
Publicado: (2025)

Understanding and Benchmarking Artificial Intelligence: OpenAI's o3 Is Not AGI
por: Pfister, Rolf, et al.
Publicado: (2025)

FlexQuant: Elastic Quantization Framework for Locally Hosted LLM on Edge Devices
por: Chai, Yuji, et al.
Publicado: (2025)