amd-shark
/

sdxl-quant-fp8

Model card Files Files and versions Community

4 contributors

History: 16 commits

GiusFra's picture

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

b8d5ec9 verified 4 months ago

all_linear_sym_8_calib10
MI250 QKV fused and all linear layers sym, FP8 attention, guidance scale 8, calib steps 8 4 months ago
all_linear_sym_8_calib8
Fix names 4 months ago
all_sym_8_calib10
MI250 QKV fused and all layers sym, FP8 attention, guidance scale 8, calib steps 10 4 months ago
brevitas
updated quant_params with QKV fusion 5 months ago
.gitattributes

1.73 kB

MI250 QKV fused and all linear layers sym, FP8 attention, guidance scale 8, calib steps 10 4 months ago
sdxl.json

2.19 MB

Upload sdxl.json with huggingface_hub 6 months ago
sdxl.safetensors

5.14 GB
LFS

Upload sdxl.safetensors with huggingface_hub 6 months ago