Ignore MatMul due to non constant B: /[/transformer/layers.0/self_attn/MatMul]

When I run the code below in the notebook "onnx_model_example.ipynb", a warning occurs:
`quantize_dynamic(
model_input=onnx_model_path,
model_output=onnx_model_quantized_path,
optimize_model=True,
per_channel=False,
reduce_range=False,
weight_type=QuantType.QUInt8,
)
onnx_model_path = onnx_model_quantized_path`
the warning is:
`Ignore MatMul due to non constant B: /[/transformer/layers.0/self_attn/MatMul]
Ignore MatMul due to non constant B: /[/transformer/layers.0/self_attn/MatMul_1]
Ignore MatMul due to non constant B: /[/transformer/layers.0/cross_attn_token_to_image/MatMul]
Ignore MatMul due to non constant B: /[/transformer/layers.0/cross_attn_token_to_image/MatMul_1]
Ignore MatMul due to non constant B: /[/transformer/layers.0/cross_attn_image_to_token/MatMul]
Ignore MatMul due to non constant B: /[/transformer/layers.0/cross_attn_image_to_token/MatMul_1]
Ignore MatMul due to non constant B: /[/transformer/layers.1/self_attn/MatMul]
Ignore MatMul due to non constant B: /[/transformer/layers.1/self_attn/MatMul_1]
Ignore MatMul due to non constant B: /[/transformer/layers.1/cross_attn_token_to_image/MatMul]
Ignore MatMul due to non constant B: /[/transformer/layers.1/cross_attn_token_to_image/MatMul_1]
Ignore MatMul due to non constant B: /[/transformer/layers.1/cross_attn_image_to_token/MatMul]
Ignore MatMul due to non constant B: /[/transformer/layers.1/cross_attn_image_to_token/MatMul_1]
Ignore MatMul due to non constant B: /[/transformer/final_attn_token_to_image/MatMul]
Ignore MatMul due to non constant B: /[/transformer/final_attn_token_to_image/MatMul_1]
Ignore MatMul due to non constant B: /[/MatMul_1]`

Will this affect the performance of the SAM?

Start with onnx_model_example.ipynb and the quantize_dynamic call shown in the report. Inspect how the non-constant B MatMul warnings are produced, then compare SAM inference behavior and performance before and after quantization; done means documenting whether the warnings change model correctness or performance.

Written by the indexing model from the issue text.