CreateI8F32UniformQuantizedPerAxisType(
          UnknownLoc::get(&ctx_), ctx_,
          /*scales=*/SmallVector<double, 2>{1.0, 1.0},
          /*zero_points=*/SmallVector<int64_t, 2>{0, 0},
          /*quantization_dimension=*/0);

  // Storage type of `i8` is currently verifiable as `unsigned` in `Types.cpp`.
  EXPECT_TRUE(quantized_type.getStorageType().isSignlessInteger(8));
}

              /*narrow_range=*/true, /*legacy_float_scale=*/false));
    } else {
      int quantization_dimension = GetQuantizationDimension(
          weight_only_ptq, cast<TF::XlaCallModuleOp>(quantizable_op));
      weight_type = quant::GetUniformQuantizedPerAxisTypeForWeight(
          attr, quantization_dimension, /*symmetric=*/true, /*num_bits=*/8,
          /*is_signed=*/true,

    const int64_t quantization_dimension =
        mlir::cast<ShapedType>(filter_type).getShape().size() - 1;
    accumulation_quantized_element_type =
        CreateI32F32UniformQuantizedPerAxisType(
            gemm_style_op->getLoc(), *rewriter.getContext(), result_scales,
            zero_points, quantization_dimension);

  // zero_points correspond to. For example, a tensor t, with dims=[4, 3, 2, 1]
  // with quantization params:
  //   scale=[1.0, 2.0, 3.0], zero_point=[1, 2, 3], quantization_dimension=1
  // will be quantized across the second dimension of t.
  //   t[:, 0, :, :] will have scale[0]=1.0, zero_point[0]=1
  //   t[:, 1, :, :] will have scale[1]=2.0, zero_point[0]=2

  // zero_points correspond to. For example, a tensor t, with dims=[4, 3, 2, 1]
  // with quantization params:
  //   scale=[1.0, 2.0, 3.0], zero_point=[1, 2, 3], quantization_dimension=1
  // will be quantized across the second dimension of t.
  //   t[:, 0, :, :] will have scale[0]=1.0, zero_point[0]=1
  //   t[:, 1, :, :] will have scale[1]=2.0, zero_point[0]=2

  // zero_points correspond to. For example, a tensor t, with dims=[4, 3, 2, 1]
  // with quantization params:
  //   scale=[1.0, 2.0, 3.0], zero_point=[1, 2, 3], quantization_dimension=1
  // will be quantized across the second dimension of t.
  //   t[:, 0, :, :] will have scale[0]=1.0, zero_point[0]=1
  //   t[:, 1, :, :] will have scale[1]=2.0, zero_point[0]=2