[TFLite] TFLite FP16 Post Quantization Support

[FrozenGene]

TensorFlow Lite now supports converting weights to 16-bit floating point values during model conversion from TensorFlow to TensorFlow Lite's flat buffer format. This results in a 2x reduction in model size.

However, this will insert new dequantize for ops (like conv2d) used for dequantize fp16 weight to fp32. Like this:

TVM doesn't support this behavior. List the things we mainly should to do:

• Support float16 type inside tflite parser
• Extend dequantize to support fp16 to fp32

Related issue:#5774

[onkar-sima-ai]

@FrozenGene Is this issue still open?

[FrozenGene]

@FrozenGene Is this issue still open?

I think #7093 is enough and could close it now.