amd
/

gpt-oss-20b-WFP8-AFP8-KVFP8

Model card Files Files and versions

KV cache quantization in FP8

#1

by XuebinWang - opened Nov 4, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

AMD org Nov 4, 2025

No description provided.

initial commit to firstly support kv cache quantization in FP8e370f343

XuebinWang changed pull request status to open Nov 4, 2025

XuebinWang changed pull request status to merged Nov 4, 2025

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