Tag feed

#webgpu

58 posts11 followers

Explore Hashnode

Alternatives

Trending tags this week

ZZyVOPzyvop.hashnode.dev14h ago · 8 min read

The Deathray: A Simple Way for an Untrusted Site to Freeze a Mac

One Link, One Infinite Loop, One Frozen Mac: Meet the Deathray Okay, I need to talk about this thing going around called the Deathray, because it might be the most delightfully unhinged security story

0

MDMartin Delophymartindelophy.hashnode.devAug 4 · 10 min read

Why Browser-Based Multilingual TTS Kept Freezing at 86% — and How We Fixed It

Running text-to-speech entirely in the browser sounds straightforward: download an ONNX model, create an inference session, and synthesize audio without sending user text or media to a server. In prod

0

MDMartin Delophymartindelophy.hashnode.devJul 29 · 8 min read

Building Stable Video Portrait Outlines in the Browser with MODNet, SlimSAM, MediaPipe, and Optical Flow

A portrait outline effect looks simple: find a person and draw a line around them. In real video, however, the problem quickly expands into subject identity, fine matting, temporal stability, occlusio

0

MDMartin Delophymartindelophy.hashnode.devJul 27 · 9 min read

Removing Video Watermarks Locally with MI-GAN, ONNX Runtime Web, and WebGPU

Watermark and unwanted-object removal looks straightforward in a model demo. Inside a real video editor, it becomes a much larger systems problem. The conventional architecture uploads media to a GPU

0

MDMartin Delophymartindelophy.hashnode.devJul 26 · 6 min read

Building In-Browser AI Music Generation: WebGPU, ONNX Optimization, and Long-Audio Stitching Tricks

Introduction Running AI models entirely in the browser is no longer a futuristic experiment. With WebGPU and ONNX Runtime, we can now run diffusion-based audio models 100% locally, without any backend

0

KSKuldeep Singhar5en1c.hashnode.devJul 17 · 11 min read

Why an on-device LLM broke on half the Windows machines it ran on, and the one-line kind of fix that brought it back

On-device AI has a quiet promise: the model runs in your browser, your data never leaves your machine, and there is no server bill. In 2026 that promise got real. A 2 GB build of Gemma 4 now runs enti

0

Sswathikbuildinginthebrowser.hashnode.devJul 3 · 10 min read

Running a background-removal neural net in the browser, with no two devices treated the same

Every "AI background remover, 100% in the browser" demo you've ever clicked runs beautifully. On the author's MacBook. Then someone opens it on a three-year-old Android, the tab spins for forty second

0

ATAbhinav T Bblog.abhinavtb.comMay 23 · 10 min read

VaultClip: Building Private Video Q&A Fully in the Browser

I built VaultClip because I wanted a simple thing that still feels surprisingly hard to get today: upload a video, ask questions about it, and get useful answers ,without sending the video to someone

0

PKPrashant Koiralablog.prashantkoirala.info.npMay 3 · 8 min read

Local first AI is coming back

AI on the web has mostly meant one thing: send user input to an API, wait for a cloud model, then render the answer. That model is not going away. Large frontier models still need serious compute. But

0

GVGaurav Vishwakarmablogs.gaurav.oneApr 27 · 7 min read

Harnessing Apple M-Series GPUs for Local AI in Web Development: A 2025 Guide

You're a web developer, constantly pushing the boundaries of what's possible in the browser and on the server. For years, integrating sophisticated Artificial Intelligence into web applications often meant hefty cloud bills, data privacy concerns, or...

0

#webgpu

Search Hashnode

#webgpu

Explore Hashnode

Trending tags this week

The Deathray: A Simple Way for an Untrusted Site to Freeze a Mac

Why Browser-Based Multilingual TTS Kept Freezing at 86% — and How We Fixed It

Building Stable Video Portrait Outlines in the Browser with MODNet, SlimSAM, MediaPipe, and Optical Flow

Removing Video Watermarks Locally with MI-GAN, ONNX Runtime Web, and WebGPU

Building In-Browser AI Music Generation: WebGPU, ONNX Optimization, and Long-Audio Stitching Tricks

Why an on-device LLM broke on half the Windows machines it ran on, and the one-line kind of fix that brought it back

Running a background-removal neural net in the browser, with no two devices treated the same

VaultClip: Building Private Video Q&A Fully in the Browser

Local first AI is coming back

Harnessing Apple M-Series GPUs for Local AI in Web Development: A 2025 Guide