feat(default.py): support ViT (OpenPPL#145)

* feat(default.py): add support ViT opr

* docs(torch.py): remove useless

fix bugs: fixed calib_steps (OpenPPL#42)

Fixed quantized function not being able to modify Calib Steps

Update ssd.py (OpenPPL#33)

Ensure the variables are on the same device.

Update to 0.6.1

Support ONNXRuntime Quant&Dequant Format.

Core update to 0.6.0

Add Subgraph Optimization Algorithm
Add Matrix Factorization Algorithm
Add 4&8 bit Mix Precision Dispatching
Refine Network Analysis
Add ProgramEntrance.py (as an usage example)
Other bug fixs.

Update to version 0.5.3

Update to 0.5.3
Channel Split Algorithm Added
MSE Calibration method Added
bn merge bugs fixed
cuda.histogram bugs fixed
fix other typos.
README updated.

initial import