FP16 Quantization Made Our In-Browser Real-ESRGAN 4.8x Faster — and Nearly Destroyed Our Inpainting Model
This story is from 2026-10-04. It is preserved in the archive; the latest stories are on the live feed.
We run super-resolution and watermark removal entirely in the browser at ClearPix, using ONNX Runtime Web on WebGPU. This post is the writeup of one optimization round that produced our single biggest inference speedup — 4.8x at page level from fp16 quantization — and, in the same week, two of our…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-04 09:19 · DEV Community — Machine Learning
FP16 Quantization Made Our In-Browser Real-ESRGAN 4.8x Faster — and Nearly Destroyed Our Inpainting Model