`TFLiteConverter.from_saved_model`.
    *   The Python TF Lite Interpreter bindings now has an option
        `experimental_preserve_all_tensors` to aid in debugging conversion.
    *   Quantized x86 execution defaults to Ruy GEMM library for platforms with
        AVX support.
    *   Deprecate
        `tf.compat.v1.lite.experimental.get_potentially_supported_ops`. Use
        `tf.lite.TFLiteConverter` directly to check whether a model is