[converter] TFLite schema update

According to user feedback, the current supported ops are not sufficient for model deployment. This requires a major update of the existing TFLite schema. Currently, we are using the schema of TFLite 2.3.0.

After a quick skimming of the current TF operator list (as of TFLite 2.8.0), if we consider updating it to the latest schema, we will have support for the builtin ops include
- [ ] GELU
- [x] CONV_3D
- [x] CONV_3D_TRANSPOSE
- [ ] RANDOM_STANDARD_NORMAL
- [ ] RANDOM_UNIFORM
- [x] CUMSUM
- [ ] BROADCAST_TO
- and [more](https://github.com/tensorflow/tensorflow/blob/v2.8.0/tensorflow/lite/kernels/register.cc#L312-L341)

We may also add support to the following custom kernels if users choose to build TFLite from source.
- [ ] GRU
- [ ] AVG_POOL3D
- [ ] MAX_POOL3D
- [ ] CTC
- [x] ATAN2
- [ ] SIGN
- and more

Start by locating the converter's existing TFLite 2.3.0 schema and compare it with the TFLite 2.8.0 operator list linked in the issue. Determine which builtin and optional custom kernels are in scope, then define completion as updating the schema and verifying support for the selected checklist items.

Written by the indexing model from the issue text.