amd-shark
/

sdxl-quant-fp8

Model card Files Files and versions Community

sdxl-quant-fp8 / linear_conv_fp8_sdpa_fp16_no_eq_bl

Commit History

Create config.json

864a3a2
verified

GiusFra commited on Oct 1

Added models that are fully quantized with FP8.

cfd94d7

nickfraser commited on Sep 10