Quantization aware adapter testing

#30

by jbakerx - opened Dec 18, 2025

Make sure the adapter behaves under common serving setups:

8-bit / 4-bit quantization
different inference kernels
Document “known-good” settings on the model card.

Owner Dec 24, 2025

We will consider this enhancement for inclusion in version 2.0.0.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment