Hugging Face's logo

amd-shark
/
sdxl-quant-int8

Transformers
Inference Endpoints
Model card Files Community
2
sdxl-quant-int8

Commit History

Fix (script): Quantize output of QuantLora layers.
77d84b5

nickfraser commited on

Fix (script): print output directory.
e6b40f3

nickfraser commited on

Feat (script): Added calibration size argument.
8324b6e

nickfraser commited on

Fix (minimal): Move to CPU before export
13b9094

nickfraser commited on

Quantization script
ecec5b7
verified

GiusFra commited on

Remove potential overflow / saturation error.
161df88

nickfraser commited on

Added comments - highlight possible overflow situation
3f5851c

nickfraser commited on

Updated math model to target int8 x int8 kernels.
4024f9d

nickfraser commited on

Updated QOp model to fuse SmoothQuant scales with input quantization
dca9b6e

nickfraser commited on

Output reference tensors
8e3c05a
verified

GiusFra commited on

Add config.json from stable-diffusion-xl-base-1.0/unet
54be8be

Stella Laurenzo commited on

Upload params.safetensors with huggingface_hub
1dad0d1
verified

GiusFra commited on

add missing smoothquant factors
99e9d19
verified

GiusFra commited on

update quant_params with correct shapes
d6a388a
verified

GiusFra commited on

Fix: set `keepdim=True`
9ab1060

nickfraser commited on

[test] Fixed shapes to match new `quant_param.json`
673c9f2

nickfraser commited on

[math_model/test] Added "QOp" implementation and basic tests.
eb5a5f6

nickfraser commited on

Upload quant_param.json with huggingface_hub
d67ece3
verified

GiusFra commited on

Upload quant_param.json with huggingface_hub
bcd05a6
verified

GiusFra commited on

Upload math_model.py with huggingface_hub
049c65f
verified

GiusFra commited on

Upload params.safetensors with huggingface_hub
742c3ad
verified

GiusFra commited on

Upload params.safetensors with huggingface_hub
76a91d8
verified

GiusFra commited on

Upload quant_param.json with huggingface_hub
01fc5a5
verified

GiusFra commited on

Upload math_model.py with huggingface_hub
d5dfd96
verified

GiusFra commited on

Upload quant_param.json with huggingface_hub
88730c2
verified

GiusFra commited on