amd-shark
/

sdxl-quant-int8

Inference Endpoints

Model card Files Files and versions Community

sdxl-quant-int8 / math_model.py

Commit History

Update quant params structure (#2)

6b62ce4
verified

nickfraser commited on Jul 3, 2024

Remove potential overflow / saturation error.

161df88

nickfraser commited on Jun 19, 2024

Added comments - highlight possible overflow situation

3f5851c

nickfraser commited on Jun 19, 2024

Updated math model to target int8 x int8 kernels.

4024f9d

nickfraser commited on Jun 19, 2024

Updated QOp model to fuse SmoothQuant scales with input quantization

dca9b6e

nickfraser commited on Jun 18, 2024

Fix: set `keepdim=True`

9ab1060

nickfraser commited on Jun 11, 2024

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

eb5a5f6

nickfraser commited on Jun 11, 2024

Upload math_model.py with huggingface_hub

049c65f
verified

GiusFra commited on Jun 7, 2024

Upload math_model.py with huggingface_hub

d5dfd96
verified

GiusFra commited on Jun 7, 2024