DEV Community

#webgpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How we validated a from-scratch WebGPU LLM engine, number by number, against llama.cpp
dagoalguez profile

How we validated a from-scratch WebGPU LLM engine, number by number, against llama.cpp

#webgpu #llm #opensource #testing
Comments 2
7 min read
Stop Uploading Product Images to a Server Just to Remove a Background
jojo_willnn_ profile

Stop Uploading Product Images to a Server Just to Remove a Background

#webdev #javascript #webgpu #performance
Comments
3 min read
Three things that broke when I moved AI image models into the browser
mno_tao_236ab4649edf4cf9f profile

Three things that broke when I moved AI image models into the browser

#webgpu #javascript #machinelearning #webdev
Comments 2
3 min read
SysVis.AI: Running Architecture Diagramming AI 100% Locally in the Browser with WebGPU
khoavo profile

SysVis.AI: Running Architecture Diagramming AI 100% Locally in the Browser with WebGPU

#ai #webgpu #javascript #opensource
Comments
3 min read
I built a real-time flood digital twin of a UK river that runs entirely in the browser, GPU and on-device AI included
fortitudeomnis profile

I built a real-time flood digital twin of a UK river that runs entirely in the browser, GPU and on-device AI included

#showdev #webgpu #javascript #ai
1
Comments
4 min read
Write the reference before debugging the shader
sarthakagrawal927 profile

Write the reference before debugging the shader

#webgpu #machinelearning #testing #devlog
Comments
1 min read
I Built a RAG AI Assistant That Runs in the Browser with WebGPU
sdx_development profile

I Built a RAG AI Assistant That Runs in the Browser with WebGPU

#ai #webdev #webgpu #rag
7
Comments 4
4 min read
The browser-training speedup was a curve, not one headline number
sarthakagrawal927 profile

The browser-training speedup was a curve, not one headline number

#webgpu #performance #machinelearning #devlog
Comments
1 min read
The more aggressive matmul kernel lost to the register budget
sarthakagrawal927 profile

The more aggressive matmul kernel lost to the register budget

#webgpu #performance #machinelearning #devlog
Comments
1 min read
Dai 5x ai 10x: come spremere WebGPU per l’inferenza AI nel browser
frontendfacile profile

Dai 5x ai 10x: come spremere WebGPU per l’inferenza AI nel browser

#webgpu #inferenzanelbrowser #kernelgpu #fusiondelleoperazion
4
Comments
3 min read
Unlocking Client-Side AI: Running LLMs in the Browser with WebGPU
lightningdev123 profile

Unlocking Client-Side AI: Running LLMs in the Browser with WebGPU

#webgpu #ai #webdev #llm
6
Comments
7 min read
AI on-device nel browser con Transformers.js: pipeline, modelli ONNX e accelerazione con WebGPU
frontendfacile profile

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

#transformersjs #webgpu #onnxruntimeweb #pipelineml
Comments
4 min read
On-Device Computer Vision Under 16 Milliseconds
techamit95ch profile

On-Device Computer Vision Under 16 Milliseconds

#aiengineering #computervision #webgpu #performance
Comments 1
6 min read
What breaks when you ship 21 AI tools that never touch a server
kingcavan1988 profile

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

#webdev #javascript #ai #webgpu
Comments
5 min read
WebGPU LLM Inference: Running 7B Models Natively in the Browser
aomiqaza profile

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

#aiengineering #webgpu
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.