Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for unpack_quantized_types_ (0.33 sec)

  1. tensorflow/compiler/mlir/quantization/stablehlo/cc/config_test.cc

      EXPECT_TRUE(new_config.pipeline_config().unpack_quantized_types());
    }
    
    TEST(PopulateDefaultsTest, PopulateDefaultsForConfigWithUnpackQuantizedTypes) {
      QuantizationConfig config{};
      config.mutable_pipeline_config()->set_unpack_quantized_types(false);
    
      // Test that if the user explicitly provided `unpack_quantized_types`, it is
      // not overridden.
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 06:59:34 UTC 2024
    - 12K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/quantization/stablehlo/quantization_config.proto

      // without uniform quantized types (mostly i8 or i32). Useful when the target
      // hardware performs better with integer ops.
      // Default value: true
      optional bool unpack_quantized_types = 1;
    
      // When set to True, requantize op in the quantized fusion will merge with the
      // subsequent dequantize op if present.
      // Default value: false
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Fri May 17 03:36:50 UTC 2024
    - 14.3K bytes
    - Viewed (0)
Back to top