Imagen de Portada

Reducing Compute Waste in LLMs through Kernel-Level DVFS

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Spaan, Jeffrey, Chen, Kuan-Hsun, Varbanescu, Ana-Lucia
Formato:	Preprint
Publicado:	2026
Materias:	Performance Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

WCDT: Systematic WCET Optimization for Decision Tree Implementations
por: Hölscher, Nils, et al.
Publicado: (2025)

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
por: Wang, Han, et al.
Publicado: (2026)

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search
por: Jaber, Jaber, et al.
Publicado: (2026)

Cloud Computing Energy Consumption Prediction Based on Kernel Extreme Learning Machine Algorithm Improved by Vector Weighted Average Algorithm
por: Wang, Yuqing, et al.
Publicado: (2025)

KernelBench: Can LLMs Write Efficient GPU Kernels?
por: Ouyang, Anne, et al.
Publicado: (2025)

DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
por: Wang, Liangyu, et al.
Publicado: (2025)

A Kernel-Based Approach for Accurate Steady-State Detection in Performance Time Series
por: Beseda, Martin, et al.
Publicado: (2025)

Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach
por: Zhang, Yijia, et al.
Publicado: (2024)

InTreeger: An End-to-End Framework for Integer-Only Decision Tree Inference
por: Bart, Duncan, et al.
Publicado: (2025)

SAfEPaTh: A System-Level Approach for Efficient Power and Thermal Estimation of Convolutional Neural Network Accelerator
por: Chen, Yukai, et al.
Publicado: (2024)

Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU
por: Jiang, Jevin, et al.
Publicado: (2026)

Conformer-Based Speech Recognition On Extreme Edge-Computing Devices
por: Xu, Mingbin, et al.
Publicado: (2023)

A Structure-Aware Framework for Learning Device Placements on Computation Graphs
por: Duan, Shukai, et al.
Publicado: (2024)

DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
por: Holmes, Connor, et al.
Publicado: (2024)

FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention
por: Gupta, Ahan, et al.
Publicado: (2023)

Flex Attention: A Programming Model for Generating Optimized Attention Kernels
por: Dong, Juechu, et al.
Publicado: (2024)

Towards Computational Performance Engineering for Unsupervised Concept Drift Detection -- Complexities, Benchmarking, Performance Analysis
por: Werner, Elias, et al.
Publicado: (2023)

Accuracy and Consumption analysis from a compressed model by CompactifAI from Multiverse Computing
por: Fovet, Damien, et al.
Publicado: (2025)

GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
por: Andrews, Martin, et al.
Publicado: (2025)

GCL-Sampler: Discovering Kernel Similarity for Sampled GPU Simulation via Graph Contrastive Learning
por: Wang, Jiaqi, et al.
Publicado: (2026)

Revisiting Forest Proximities via Sparse Leaf-Incidence Kernels
por: Aumon, Adrien, et al.
Publicado: (2026)

EXAQ: Exponent Aware Quantization For LLMs Acceleration
por: Shkolnik, Moran, et al.
Publicado: (2024)

LLMs for Analog Circuit Design Continuum (ACDC)
por: Esfandiari, Yasaman, et al.
Publicado: (2025)

Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design
por: Huang, Zixiao, et al.
Publicado: (2025)

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
por: Hourri, Younes, et al.
Publicado: (2025)

Kevin: Multi-Turn RL for Generating CUDA Kernels
por: Baronio, Carlo, et al.
Publicado: (2025)

DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs
por: Liu, Jiahui, et al.
Publicado: (2024)

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
por: Yun, Vincent-Daniel, et al.
Publicado: (2026)

Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
por: Panigrahy, Deepak, et al.
Publicado: (2026)

MoEITS: A Green AI approach for simplifying MoE-LLMs
por: Balderas, Luis, et al.
Publicado: (2026)

OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction
por: Mozaffari, Mohammad, 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)

lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models
por: Wang, Haoxin, et al.
Publicado: (2025)

Anatomizing Deep Learning Inference in Web Browsers
por: Wang, Qipeng, et al.
Publicado: (2024)

MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation
por: Wen, Zhongzhen, et al.
Publicado: (2025)

Application Research On Real-Time Perception Of Device Performance Status
por: Wang, Zhe, et al.
Publicado: (2024)

oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation
por: Li, Jianhui, et al.
Publicado: (2023)

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

DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing
por: Boudaoud, Afif, et al.
Publicado: (2025)

A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations
por: Flavin, Timothy, et al.
Publicado: (2026)