and then performs quantized convolution on quantized `lhs` and `rhs`.

The internal quantization on `lhs` is a quantization to `Trhs`, dynamic range,
per-batch (per-axis along axis `dimension_numbers.input_batch_dimension`), asymmetric,
and not narrow range (the range is [Trhs_MIN, Trhs_MAX]).

`lhs` and `rhs` must be Tensors of same rank, and meet following shape conditions.
- lhs_feature % feature_group_count == 0

        `TFLiteConverter.from_saved_model`.
    *   Added DEPTH_TO_SPACE support in Post training quantization.
    *   Added dynamic range quantization support for the BatchMatMul op.
        *   Both symmetric and asymmetric quantized input tensor are supported.
    *   Add `RFFT2D` as builtin op. (`RFFT2D` also supports `RFFTD`.) Currently
        only supports float32 input.
    *   Add 5D support to `SLICE` op.

2066..2069    ; disallowed                             # 6.3  LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE
206A..206F    ; disallowed                             # 1.1  INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
2070          ; mapped                 ; 0030          # 1.1  SUPERSCRIPT ZERO
2071          ; mapped                 ; 0069          # 3.2  SUPERSCRIPT LATIN SMALL LETTER I