inference/research
verifiedhigh · 0.90updated 2026-10-03

optimum-quanto README

repo

Fields

id
sources/quant-quanto-readme
URL
https://github.com/huggingface/optimum-quanto
Publisher
Hugging Face
Kind
repo
Published
2026-10-03
Accessed
2026-10-03
notes
Lists int2/int4/int8/float8 weights, int8/float8 activations, and the CUDA int8-int8 / fp16-int4 / bf16-int8 / bf16-int4 kernels.

Notes

Lists int2/int4/int8/float8 weights, int8/float8 activations, and the CUDA int8-int8 / fp16-int4 / bf16-int8 / bf16-int4 kernels.

Cross-references

This record references no other records.