[inductor] add conv_transpose2d unary fusion for cpu in inference mode (#90265)
An FX transformation is added to fuse ConvTranspose2d with eltwise OPs in torchinductor for CPU in inference mode, following the implementation in https://github.com/pytorch/pytorch/pull/87063.
The fusion OP is implemented in https://github.com/pytorch/pytorch/pull/90264 and will be treated as an extern kernel call in torchinductor.
The fusion of ConvTranspose2d with the below OPs is supported:
- relu
- sigmoid
- tanh
- hardswish
- leaky_relu
- hardtanh
- gelu
Pull Request resolved: https://github.com/pytorch/pytorch/pull/90265
Approved by: https://github.com/jgong5, https://github.com/jansel
