Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for addConversion (0.12 sec)

  1. tensorflow/compiler/mlir/quantization/stablehlo/passes/convert_func_to_bfloat16.cc

    #include "tensorflow/core/platform/bfloat16.h"
    
    namespace mlir::quant::stablehlo {
    namespace {
    
    class BFloat16TypeConverter : public TypeConverter {
     public:
      BFloat16TypeConverter() {
        addConversion([](const Type type) -> Type {
          return IsLargeFloatType(type) ? ToBfloat16Type(type) : type;
        });
      }
    };
    
    // This helper function makes legality check easier. Both convert ops in the
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 9.3K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf_with_tf2xla.cc

      // Currently, we don't do any type conversions. Any TensorFlow op with a type
      // that is not supported in MHLO will fail conversion. Quantized types are
      // going to handled separately so we don't need to handle those.
      addConversion([](Type ty) { return ty; });
    
      // This materialization is helpful in cases where we have more refined types
      // after conversion to mhlo compared to the original type in TF. For example,
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 28 21:49:50 UTC 2024
    - 9.7K bytes
    - Viewed (0)
Back to top