Cover Image

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Maczan, Jędrzej
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Distributed, Parallel, and Cluster Computing Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU
by: Levine, Reese, et al.
Published: (2026)

Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
by: Li, Zhuojin, et al.
Published: (2025)

TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
by: Vellaisamy, Prabhu, et al.
Published: (2026)

LEO: Tracing GPU Stall Root Causes via Cross-Vendor Backward Slicing
by: Xia, Yuning, et al.
Published: (2026)

GPU Cluster Scheduling for Network-Sensitive Deep Learning
by: Sharma, Aakash, et al.
Published: (2024)

LLMPerf: GPU Performance Modeling meets Large Language Models
by: Nguyen, Khoi N. M., et al.
Published: (2025)

Towards Universal Performance Modeling for Machine Learning Training on Multi-GPU Platforms
by: Lin, Zhongyi, et al.
Published: (2024)

HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
by: Lin, Mao, et al.
Published: (2026)

A Practical Two-Stage Framework for GPU Resource and Power Prediction in Heterogeneous HPC Systems
by: Oztop, Beste, et al.
Published: (2026)

xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads
by: Shi, Jiabo, et al.
Published: (2025)

Prism: Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving
by: Yu, Shan, et al.
Published: (2025)

KEET: Explaining Performance of GPU Kernels Using LLM Agents
by: Davis, Joshua H., et al.
Published: (2026)

GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs
by: Chu, Ruifan, et al.
Published: (2025)

Efficient allocation of image recognition and LLM tasks on multi-GPU system
by: Lawenda, Marcin, et al.
Published: (2025)

KVDirect: Distributed Disaggregated LLM Inference
by: Chen, Shiyang, et al.
Published: (2024)

Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC
by: Siavashi, Mohammad, et al.
Published: (2026)

Optimizing Attention on GPUs by Exploiting GPU Architectural NUMA Effects
by: Choudhary, Mansi, et al.
Published: (2025)

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference
by: Hamadanian, Pouya, et al.
Published: (2025)

The Energy Cost of Execution-Idle in GPU Clusters
by: Lei, Yiran, et al.
Published: (2026)

Scalable GPU Performance Variability Analysis framework
by: Lahiry, Ankur, et al.
Published: (2025)

On the Partitioning of GPU Power among Multi-Instances
by: Vamja, Tirth, et al.
Published: (2025)

Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
by: Vellaisamy, Prabhu, et al.
Published: (2025)

Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search
by: Nichols, Daniel, et al.
Published: (2026)

KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation
by: Jiang, Chaoyi, et al.
Published: (2024)

Disaggregated Design for GPU-Based Volumetric Data Structures
by: Meneghin, Massimiliano, et al.
Published: (2025)

Taking GPU Programming Models to Task for Performance Portability
by: Davis, Joshua H., et al.
Published: (2024)

Profiling and optimization of multi-card GPU machine learning jobs
by: Lawenda, Marcin, et al.
Published: (2025)

CUTHERMO: Understanding GPU Memory Inefficiencies with Heat Map Profiling
by: Zhao, Yanbo, et al.
Published: (2025)

High-Performance Portable GPU Primitives for Arbitrary Types and Operators in Julia
by: Pilliat, Emmanuel
Published: (2026)

Data-Driven Analysis to Understand GPU Hardware Resource Usage of Optimizations
by: Islam, Tanzima Z., et al.
Published: (2024)

Minos: Systematically Classifying Performance and Power Characteristics of GPU Workloads on HPC Clusters
by: Jain, Rutwik, et al.
Published: (2026)

Efficient GPU-Centered Singular Value Decomposition Using the Divide-and-Conquer Method
by: Liu, Shifang, et al.
Published: (2025)

Unleashing the Power of Preemptive Priority-based Scheduling for Real-Time GPU Tasks
by: Wang, Yidi, et al.
Published: (2024)

Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs
by: Wahlgren, Jacob, et al.
Published: (2025)

Fast and Scalable Mixed Precision Euclidean Distance Calculations Using GPU Tensor Cores
by: Curless, Brian, et al.
Published: (2025)

Multi-DNN Inference of Sparse Models on Edge SoCs
by: Luo, Jiawei, et al.
Published: (2026)

IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency
by: Ghafouri, Saeid, et al.
Published: (2023)

CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference
by: Xu, Guanyu, et al.
Published: (2025)

AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference
by: Zhao, Xuanlei, et al.
Published: (2024)

InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update
by: Wu, Dan, et al.
Published: (2023)