Webgpu

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Sarthak Agrawal

Sep 13

The more aggressive matmul kernel lost to the register budget

#webgpu #performance #machinelearning #devlog

1 min read

frontendfacile.it

Sep 8

AI on-device nel browser con Transformers.js: pipeline, modelli ONNX e accelerazione con WebGPU

#transformersjs #webgpu #onnxruntimeweb #pipelineml

4 min read

Amit chakraborty

Sep 11

On-Device Computer Vision Under 16 Milliseconds

#aiengineering #computervision #webgpu #performance

6 min read

Dazhi Wang

Sep 6

What breaks when you ship 21 AI tools that never touch a server

#webdev #javascript #ai #webgpu

5 min read

Aomi Qaza

Aug 15

WebGPU LLM Inference: Running 7B Models Natively in the Browser

#aiengineering #webgpu

4 min read

JH5

Aug 13

瀏覽器跑 LLM 的實際體感與骨感限制

#webgpu #webassembly #llm #browser

2 min read

Karol Rybak

Aug 8

Introducing CHOMATO: A lightweight harness for LFM 2.5 with superpowers.

#ai #programming #typescript #webgpu

1 min read

MartinDelophy

Aug 5

Building Cinematic Depth in the Browser with Depth Anything V2 Small and WebGPU

#opensource #ai #webgpu #javascript

6 min read

MartinDelophy

Aug 4

DEV Community

#webgpu

The more aggressive matmul kernel lost to the register budget

AI on-device nel browser con Transformers.js: pipeline, modelli ONNX e accelerazione con WebGPU

On-Device Computer Vision Under 16 Milliseconds

What breaks when you ship 21 AI tools that never touch a server

WebGPU LLM Inference: Running 7B Models Natively in the Browser

瀏覽器跑 LLM 的實際體感與骨感限制

Introducing CHOMATO: A lightweight harness for LFM 2.5 with superpowers.

Building Cinematic Depth in the Browser with Depth Anything V2 Small and WebGPU

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