Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for quantization_dimension (0.17 sec)

  1. tensorflow/compiler/mlir/lite/stablehlo/transforms/compose_uniform_quantized_type_pass.cc

            CreateI8F32UniformQuantizedPerAxisType(
                filter_op->getLoc(), *rewriter.getContext(), filter_scale_values,
                filter_zero_point_values,
                /*quantization_dimension=*/3);
    
        // Create a new constant op for the filter in i8.
        auto quantized_filter_constant_op = rewriter.create<stablehlo::ConstantOp>(
            filter_op->getLoc(),
            /*output=*/
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 64.6K bytes
    - Viewed (0)
Back to top