Hugging Face's logo

amd-shark
/
sdxl-quant-int8

Transformers
Model card Files
xet
 Community
2
sdxl-quant-int8 / test_quant_linear.py

Commit History

  1. Update quant params structure (#2)⁠

    nickfraser
    Verified signature
    6b62ce4

  1. Updated math model to target int8 x int8 kernels.

    nickfraser
    4024f9d

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

    nickfraser
    673c9f2

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

    nickfraser
    eb5a5f6