WebGPU
PulseAugur coverage of WebGPU — every cluster mentioning WebGPU across labs, papers, and developer communities, ranked by signal.
- developed by World Wide Web Consortium 100%
- founded by Apple Inc. 100%
- used by WebAssembly 90%
- used by ONNX Runtime Web 90%
- uses ONNX Runtime Web 90%
- uses WebAssembly 80%
- uses WebGPU Shading Language 70%
- competes with WebGL 70%
- used by WebGL 70%
- used by PrismML 70%
- used by WebRTC 70%
- affiliated with ONNX Runtime Web 60%
10 day(s) with sentiment data
-
Ternary Bonsai 2 (27B) released, runs locally in browser
Ternary Bonsai 2, a 27-billion parameter language model, has been released on Hugging Face. This model is derived from Qwen3.8-27B and utilizes ternary weights to achieve a size of less than 6GB, which is 9 times smalle…
-
Browser-based flood digital twin uses on-device AI
A developer has created a real-time digital twin of a UK river that operates entirely within a web browser. This simulation utilizes WebGPU for rendering and incorporates on-device AI, showcasing advancements in browser…
-
Browser-based LLM inference engine Three-LLM leverages WebGPU for local execution
Ben Houston has developed Three-LLM, a WebGPU-based inference engine that allows Large Language Models (LLMs) to run locally within a web browser. This project leverages Three.js and its WebGPU capabilities to execute L…
-
AI news roundup: Codex security flaw, WebGPU highlighter, and DeepMind's genome atlas · 3 sources tracked
A security researcher has discovered that Codex, a code-generating AI model, may be making arbitrary web requests without explicit user permission. Separately, a new WebGPU-based syntax highlighter has been developed th…
-
WebGPU enables client-side LLM execution in browsers
Running large language models (LLMs) directly in web browsers is becoming feasible through the use of WebGPU, a web standard that leverages a device's graphics processing unit (GPU) for computation. Libraries like @mlc-…
-
Hugging Face releases 200+ WebGPU kernels for local AI
Hugging Face has released @huggingface/kernels, a library enabling the use of over 200 optimized WebGPU kernels for local AI applications directly from the Hugging Face Hub. These kernels cover essential machine learnin…
-
AI Creative Studio Architecture: Next.js, WebGPU, Node.js Hybrid Model
This article outlines the architecture for a full-stack AI creative studio, moving beyond traditional monolithic web development models. It proposes a hybrid, distributed system leveraging Next.js, WebGPU, and Node.js t…
-
Generative AI Media Pipelines Face New Security Threats
Generative AI media pipelines, particularly those using node-based canvases and client-side WebGPU, are vulnerable to resource exhaustion and denial-of-service attacks. Unlike traditional web services, these pipelines i…
-
WebGPU Export Engine for High-Res Canvas Rendering Detailed
This article details the creation of a WebGPU-based export engine designed to render high-resolution canvases into formats like MP4, SVG, and PDF. It addresses the common challenge in web development where interactive v…
-
AI billing systems must adapt to dynamic, GPU-heavy workflows
Building robust billing systems for GPU-intensive AI workflows is crucial for their commercial viability. These systems must translate volatile compute costs into deterministic financial units, as unoptimized pipelines …
-
Vercel open-sources vgpu WebGPU library for AI agent shaders
Vercel has open-sourced vgpu, a TypeScript library designed to simplify the development and deployment of WebGPU shaders. This library allows developers to write shaders once and run them across different environments, …
-
Generative AI Media Asset Management Needs New Architecture
Managing media assets in generative AI applications presents unique challenges compared to traditional content management systems. Generative workflows produce dynamic, algorithmically derived media, such as intermediat…
-
AI models now run directly in browsers using ONNX Runtime Web
ONNX Runtime Web is enabling complex AI tasks like background removal and feature extraction to be performed directly within a web browser. This client-side processing eliminates the need for powerful backend servers, r…
-
Spline launches major update with WebGPU rendering and AI agent
Spline has launched a completely new second version, marking a significant shift in 3D model design within browsers. This update features a WebGPU-based rendering engine for improved performance, alongside advanced mode…
-
Web tech enables real-time in-browser video editing, cutting cloud costs
Developers can now build real-time, in-browser video editors by leveraging new web technologies that shift processing from expensive cloud servers to the user's local hardware. This approach bypasses traditional bottlen…
-
VIDRAFT launches Hansu, a browser-based local AI prioritizing data sovereignty
VIDRAFT, a Korean startup, has launched Hansu, a browser-based AI assistant designed for local, client-side inference. This approach prioritizes data sovereignty, ensuring user data remains within the browser and is not…
-
WebGPU unlocks browser GPU power for massive parallel computing
WebGPU is a new web API that allows developers to leverage the massive parallel processing power of graphics processing units (GPUs) directly from the browser. Unlike its predecessor, WebGL, which was limited to renderi…
-
AI Video Workflows Shift to Event-Driven Architecture
Web developers are encountering challenges with real-time AI video workflows due to the extended processing times required for tasks like latent diffusion and WebGPU-accelerated manipulations. Traditional HTTP request-r…
-
AI image models like Stable Diffusion now run in-browser via TypeScript
New advancements in ONNX Runtime Web and WebGPU are enabling complex AI models like Stable Diffusion and Flux to run directly within web browsers using TypeScript. This shift moves AI model execution from dedicated back…
-
Infinite Canvas Performance: Spatial Indexing and WebGPU for Web Apps
This article details techniques for building high-performance infinite canvases in web applications, focusing on optimizing the rendering of thousands of generative media nodes. It highlights the challenge of maintainin…