Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

amd-shark
/
sdxl-quant-fp8

Model card Files Files and versions
xet
Community
1
sdxl-quant-fp8
Ctrl+K
Ctrl+K
  • 4 contributors
History: 37 commits
GiusFra's picture
GiusFra
Create config.json
ae57958 verified 6 months ago
  • all_linear_sym_8_calib8
    Fix names about 1 year ago
  • all_quant_int8_sdpa_fp8
    Create config.json 6 months 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
  • linear_conv_fp8_sdpa_fp16_eq_bl
    Create config.json 10 months ago
  • linear_conv_fp8_sdpa_fp16_no_eq_bl
    Create config.json 10 months ago
  • linear_conv_fp8_sdpa_fp8_eq_bl
    Create config.json 10 months ago
  • linear_conv_fp8_sdpa_fp8_no_eq_bl
    Create config.json 10 months ago
  • nvidia_fp8_unet
    Upload nvidia_fp8_unet/params.safetensors with huggingface_hub 10 months ago
  • unet_int8_sdpa_fp8_vae_int8
    Upload unet_int8_sdpa_fp8_vae_int8/vae_quant_params.json with huggingface_hub 6 months ago
  • .gitattributes
    2.25 kB
    Upload unet_int8_sdpa_fp8_vae_int8/unet_quant_params.json with huggingface_hub 6 months ago
  • attn.py
    6.26 kB
    Added SDPA math model & test about 1 year ago
  • math_model.py
    7.13 kB
    Create math_model.py 8 months 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
  • test_attn.py
    1.31 kB
    [math_model] Make it more obvious that softmax scale comes from the quantizer 8 months ago