amd-shark
/

sdxl-quant-fp8

Model card Files Files and versions

Ctrl+K

Ctrl+K

4 contributors

History: 13 commits

GiusFra's picture

MI250 QKV fused and all layers sym, FP8 attention, guidance scale 8, calib steps 10

99f92dc verified about 1 year ago

all_sym_8_calib10
MI250 QKV fused and all layers sym, FP8 attention, guidance scale 8, calib steps 10 about 1 year ago
brevitas
updated quant_params with QKV fusion about 1 year ago
.gitattributes

1.65 kB

MI250 QKV fused and all layers sym, FP8 attention, guidance scale 8, calib steps 10 about 1 year ago
sdxl.json

2.19 MB

Upload sdxl.json with huggingface_hub about 1 year ago
sdxl.safetensors

5.14 GB
xet

Upload sdxl.safetensors with huggingface_hub about 1 year ago