PostTrainingQuantConfig(quant_level='auto', device='npu', backend="onnxrt_dml_ep") produces fp32 ops.

[kleiti]

The below PostTrainingQuantConfig produces fp32 ops for NPU using 2.4.1. Models with int8 and fp16 ops would be preferred for NPU.

conf=PostTrainingQuantConfig(quant_level='auto',
device='npu', backend="onnxrt_dml_ep",
quant_format="QOperator",
approach="static",
excluded_precisions=['bf16'])

[mengniwang95]

Hi @kleiti , onnxrt_dml_ep backend is experimental and currently we only support MatMul int8. We will enhance its functionality later.