Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
amd-shark
/
sdxl-quant-fp8
like
0
Follow
AMD SHARK
20
Model card
Files
Files and versions
xet
Community
1
008bca6
sdxl-quant-fp8
Ctrl+K
Ctrl+K
4 contributors
History:
31 commits
GiusFra
Upload all_quant_int8_sdpa_fp8/quant_params.json with huggingface_hub
008bca6
verified
6 months ago
all_linear_sym_8_calib8
Fix names
about 1 year ago
all_quant_int8_sdpa_fp8
Upload all_quant_int8_sdpa_fp8/quant_params.json with huggingface_hub
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
.gitattributes
Safe
2.16 kB
Upload all_quant_int8_sdpa_fp8/quant_params.json with huggingface_hub
6 months ago
attn.py
Safe
6.26 kB
Added SDPA math model & test
about 1 year ago
math_model.py
Safe
7.13 kB
Create math_model.py
8 months ago
sdxl.json
Safe
2.19 MB
Upload sdxl.json with huggingface_hub
about 1 year ago
sdxl.safetensors
Safe
5.14 GB
xet
Upload sdxl.safetensors with huggingface_hub
about 1 year ago
test_attn.py
Safe
1.31 kB
[math_model] Make it more obvious that softmax scale comes from the quantizer
8 months ago
