amd-shark
/

sdxl-quant-int8

Inference Endpoints

Model card Files Files and versions Community

sdxl-quant-int8

4 contributors

History: 23 commits

nickfraser's picture

Fix (minimal): Move to CPU before export

13b9094 5 months ago

.gitattributes

1.57 kB

Upload quant_param.json with huggingface_hub 6 months ago
config.json

1.68 kB

Add config.json from stable-diffusion-xl-base-1.0/unet 6 months ago
math_model.py

8.55 kB

Remove potential overflow / saturation error. 5 months ago
minimal_script.py

10.2 kB

Fix (minimal): Move to CPU before export 5 months ago
out.safetensors

6.76 GB
LFS

Output reference tensors 5 months ago
params.safetensors

5.14 GB
LFS

Upload params.safetensors with huggingface_hub 6 months ago
quant_param.json

85.1 MB
LFS

add missing smoothquant factors 6 months ago
requirements.txt

223 Bytes

Quantization script 5 months ago
test_quant_conv2d.py

1.11 kB

Updated math model to target int8 x int8 kernels. 5 months ago
test_quant_linear.py

969 Bytes

Updated math model to target int8 x int8 kernels. 5 months ago