run_vit_b_quant.py runs slower than run_bit_b.py

[run_vit_b_quant.py](https://github.com/pytorch/ao/blob/main/tutorials/quantize_vit/run_vit_b_quant.py)
elapsed_time:  11.0519150390625  milliseconds


[run_bit_b.py](https://github.com/pytorch/ao/blob/main/tutorials/quantize_vit/run_vit_b.py)
elapsed_time:  1.2272755432128906  milliseconds

this is with `int8_dynamic_activation_int8_weight`

