[static runtime] refine fusion group (#49340)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49340
This refines the fusion group to include on certain types of operations. We cannot safely handle "canRunNatively" types and the memonger pass causes regressions on some internal models, so it was disabled (to be revisited with proper memory optimization once Tensor pools are implemented)
Test Plan:
```
buck test mode/no-gpu caffe2/test:static_runtime
buck test //caffe2/benchmarks/static_runtime:static_runtime_cpptest
```
Reviewed By: ZolotukhinM
Differential Revision: D25520105
fbshipit-source-id: add61d103e4f8b4615f5402e760893ef759a60a9