Upload nvidia_fp8_unet/params.safetensors with huggingface_hub

Upload nvidia_fp8_unet/quant_params.json with huggingface_hub

Upload nvidia_fp8_unet/results_mlperf.json with huggingface_hub

Upload nvidia_fp8_unet/args.json with huggingface_hub

Create config.json

Create config.json

Create config.json

Create config.json

Updated sdpa fp8 models

Added models that are fully quantized with FP8.

Added SDPA math model & test

Fix names

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

Fix names

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

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

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

updated quant_params with QKV fusion

update int8+fp8 safetensors with fused QKV

update int8+fp8 safetensors

updated quant_params for FNUZ

add missing smoothquant_mul

update int8+fp8 safetensors

update int8+fp8 safetensors

update int8+fp8 quant_param

Upload sdxl.safetensors with huggingface_hub

Upload sdxl.json with huggingface_hub

initial commit