text-generation-webui
Add Quanto4,2, HQQ4,2 KV cache quantization support to Transformers loader
#6768
Open
Open
Add Quanto4,2, HQQ4,2 KV cache quantization support to Transformers loader #6768
dinerburger
wants to merge
3 commits into
oobabooga:dev
from
dinerburger:quanto
Get quanto4,2 KV cache working in Transformers
4a55c742
Add optimum-quanto to requirements
d0ea0509
Add HQQ KV cache quantization for Transformers
244d3cb6
dinerburger
changed the title 
cceneag
requested changes
on 2025-10-08
Login to write a write a comment.
Login via GitHub