Image de couverture de livre

Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Levine, Reese, Sharma, Rithik, Jain, Nikhil, Ramesh, Abhijit, Chen, Zheyuan, Abbas, Neha, Contini, James, Sorensen, Tyler
Format:	Preprint
Publié:	2026
Sujets:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
par: Maczan, Jędrzej
Publié: (2026)

LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory
par: Sorensen, Tyler, et autres
Publié: (2024)

Efficient and Portable Support for Overdecomposition on Distributed Memory GPGPU Platforms
par: Bhosale, Aditya, et autres
Publié: (2026)

KEET: Explaining Performance of GPU Kernels Using LLM Agents
par: Davis, Joshua H., et autres
Publié: (2026)

Beyond Microservices: Testing Web-Scale RCA Methods on GPU-Driven LLM Workloads
par: Scheinert, Dominik, et autres
Publié: (2026)

Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision
par: Ringoot, Evelyne, et autres
Publié: (2025)

Taking GPU Programming Models to Task for Performance Portability
par: Davis, Joshua H., et autres
Publié: (2024)

DAK: Direct-Access-Enabled GPU Memory Offloading with Optimal Efficiency for LLM Inference
par: Lin, Shouxu, et autres
Publié: (2026)

Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems
par: Huang, En-Ming, et autres
Publié: (2025)

Mewz: Lightweight Execution Environment for WebAssembly with High Isolation and Portability using Unikernels
par: Ueda, Soichiro, et autres
Publié: (2024)

HarMoEny: Efficient Multi-GPU Inference of MoE Models
par: Doucet, Zachary, et autres
Publié: (2025)

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

Portability Efficiency Approach for Calculating Performance Portability
par: Marowka, Ami
Publié: (2024)

Understanding the Landscape of Ampere GPU Memory Errors
par: Zhu, Zhu, et autres
Publié: (2025)

Breaking the Memory Wall: A Study of I/O Patterns and GPU Memory Utilization for Hybrid CPU-GPU Offloaded Optimizers
par: Maurya, Avinash, et autres
Publié: (2024)

ParvaGPU: Efficient Spatial GPU Sharing for Large-Scale DNN Inference in Cloud Environments
par: Lee, Munkyu, et autres
Publié: (2024)

Byzantine-Tolerant Consensus in GPU-Inspired Shared Memory
par: Georgiou, Chryssis, et autres
Publié: (2025)

Accelerating Loading WebGraphs in ParaGrapher
par: Esfahani, Mohsen Koohi
Publié: (2025)

PilotANN: Memory-Bounded GPU Acceleration for Vector Search
par: Gui, Yuntao, et autres
Publié: (2025)

HAS-GPU: Efficient Hybrid Auto-scaling with Fine-grained GPU Allocation for SLO-aware Serverless Inferences
par: Gu, Jianfeng, et autres
Publié: (2025)

Toward Portable GPU Performance: Julia Recursive Implementation of TRMM and TRSM
par: Carrica, Vicki, et autres
Publié: (2025)

Portable GPU implementation of the WP-CCC ion-atom collisions code
par: Abdurakhmanov, I. B., et autres
Publié: (2024)

Web3DB: Web 3.0 RDBMS for Individual Data Ownership
par: Mukherjee, Shankha Shubhra, et autres
Publié: (2025)

Experimental Analysis of Server-Side Caching for Web Performance
par: Umar, Mohammad, et autres
Publié: (2026)

Anywhere: A Web Crawler Automation Management Interface
par: Lin, Jinwei
Publié: (2024)

GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching
par: Guo, Cong, et autres
Publié: (2024)

PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
par: Zhang, Hongbin, et autres
Publié: (2026)

Towards Portability at Scale: A Cross-Architecture Performance Evaluation of a GPU-enabled Shallow Water Solver
par: Villalobos, Johansell, et autres
Publié: (2025)

Implementing Multi-GPU Scientific Computing Miniapps Across Performance Portable Frameworks
par: Villalobos, Johansell, et autres
Publié: (2025)

Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference
par: Recasens, Pol G., et autres
Publié: (2025)

GPU Memory and Utilization Estimation for Training-Aware Resource Management: Opportunities and Limitations
par: Yousefzadeh-Asl-Miandoab, Ehsan, et autres
Publié: (2026)

AQUA: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domains
par: Kumar, Abhishek Vijaya, et autres
Publié: (2024)

PAL: A Variability-Aware Policy for Scheduling ML Workloads in GPU Clusters
par: Jain, Rutwik, et autres
Publié: (2024)

Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference
par: Yu, Minchen, et autres
Publié: (2023)

Roadrunner: Accelerating Data Delivery to WebAssembly-Based Serverless Functions
par: Marcelino, Cynthia, et autres
Publié: (2025)

Frenzy: A Memory-Aware Serverless LLM Training System for Heterogeneous GPU Clusters
par: Chang, Zihan, et autres
Publié: (2024)

Multi-Partner Project: Multi-GPU Performance Portability Analysis for CFD Simulations at Scale
par: Eleftherakis, Panagiotis-Eleftherios, et autres
Publié: (2026)

Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling
par: Ahmad, Sohaib, et autres
Publié: (2024)

KIS-S: A GPU-Aware Kubernetes Inference Simulator with RL-Based Auto-Scaling
par: Zhang, Guilin, et autres
Publié: (2025)

APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs
par: Fan, Jiakun, et autres
Publié: (2025)