Aug 2026· Informatica· Vol 50· 0 citations· 42 references
TL;DR
A lightweight BERT-inspired architecture optimized for GPU parallelmatrix operations through TensorFlow.js with the WebGPU backend is proposed, establishing a practical framework for deploying real-time edge NLP applications using open web standards and GPU acceleration.
Abstract
Large Language Models (LLMs) achieve state-of-the-art performance across natural language processingtasks but remain computationally intensive, limiting their deployment in browser-based environments.This study investigates the feasibility of real-time transformer inference entirely within web browsers usingWebGPU acceleration. We propose a lightweight BERT-inspired architecture optimized for GPUparallelmatrix operations through TensorFlow.js with the WebGPU backend. The model is evaluated ona 4,000-sample IMDB sentiment classification dataset and achieves 65–70% classification accuracy withper-sample inference latency of 8–9 ms in Google Chrome using an NVIDIA T400 GPU (4 GB VRAM).Batch inference throughput reaches approximately 6,600 inferences per minute, while GPU utilization remainsstable between 26–77%. Compared to CPU-based TensorFlow.js execution, WebGPU significantlyreduces inference latency and enables fully client-side training and inference without server dependencies.Although accuracy is lower than full-scale BERT benchmarks, the results demonstrate that simplified transformerarchitectures can operate efficiently in browser environments under resource constraints. This workestablishes a practical framework for deploying real-time edge NLP applications using open web standardsand GPU acceleration.
DataKernelBench is introduced, which translates SQL into validated PyTorch TorchPlan programs and evaluates LLMs that optimize either the core tensor-bounded snippet or the full query in CUDA or Triton through execution-guided repair and finds that higher-performing implementations commonly use kernel fusion and execution-strategy changes, stronger models benefit most from full-query specialization, and workload context matters more than hardware context.
This work integrates SmoothQuant into TorchAO and optimize the resulting inference path for Intel Xeon CPUs through graph-level fusion in TorchInductor and efficient INT8 GEMM kernel selection across oneDNN-, AVX512_VNNI-, and AMX-based implementations.
LLMVisor is presented, a roofline-guided latency attribution model that captures the memory-bound and compute-bound phases via a concise piecewise-linear form over features proportional to FLOPs and memory I/O traffic and runs efficiently at microsecond scale.
Shuowei Jin, Xueshen Liu, Jiaxin Shan et al.· 2 citations
The design of transformer-based Large Language Models (LLMs) is being radically changed through new architectures that are able to overcome scalability limitations of previous designs, including Mixture-of-Experts (MoE), Multi-Head Latent Attention (MLA), and Multi-Token Prediction (MTP). As an open-weighted model released at the end of 2024, which has both state of the art architectural transparency and production scale efficiency, DeepSeeek-V3 represents the ultimate testing ground for investigating these modern technologies. This paper provides a comprehensive analysis of the architectural structure of DeepSeek-V3 based upon information from the DeepSeek-V3 Technical Report, industry benchmarking data and independent latency testing, to demonstrate how various techniques can be used to optimize training while still providing competitive performance in code generation and mathematical reasoning. In addition, latency testing conducted on a Distilled version of DeepSeek-V3, with approximately 14 billion parameters, running on a T4 GPU, reveals that although significant improvements have been made in optimizing latency there remains substantial barriers to deploying these models. Through this context, this research will serve as a reference document for practitioners and researchers who wish to understand current trends and challenges in increasing accessibility to high performance AI models.
Yassine Zouhdi, B. Hdioud· EPJ Web of Conferences· 0 citations
Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory capacity, making offloading inference necessary to extend effective model capacity with CPU memory. Existing offloading systems, however, typically rely on coarse layer-level or expert-level scheduling, which overlooks substantial heterogeneity among tensors within the same layer and adapts poorly to changing hardware load conditions on such devices. This paper presents ATSInfer, a hybrid CPU-GPU inference system for consumer devices that performs offloading at tensor granularity. ATSInfer combines static tensor placement with load-aware dynamic transfer, and introduces asynchronous CPU-GPU coordination to efficiently schedule hardware storage, data movement, and computation across heterogeneous backends. We implement ATSInfer and evaluate it on representative consumer platforms using both dense and MoE models. Compared with existing systems, ATSInfer improves prefill throughput by up to 1.94$\times$ and decode throughput by up to 3.29$\times$, while also increasing GPU utilization and making more effective use of PCIe bandwidth. These results show that ATSInfer can substantially improve the user experience of local LLM deployment on personal consumer devices.
Yangyijian Liu, Hongyi Ye, Mingyang Li et al.· 0 citations
Large Language Models are deployed to multiple types of environments, from internet browsers to edge devices, and WebGPU serves as a modern cross-platform standard. The engines for browser-based LLM inference have proliferated, yet the overhead of WebGPU per-operation dispatch remains poorly characterized. In this work, we introduce a sequential-dispatch measurement method and show that naive single-operation measurements overestimate per-dispatch cost by conflating dispatch with synchronization. Using our method, we measure the per-dispatch cost and show that it is independent of data type used. We show that the dispatch overhead, not kernel quality, is the bottleneck at batch size 1, and isolate the dispatch count as the cause. Therefore, we conclude that at batch size 1, the effective approach to LLM inference optimization in WebGPU is reducing dispatch count. Our findings point to dispatch amortization, in the inference engines and in the WebGPU specification, as a path to practical browser-based inference.
