- Sort Score
- Result 10 results
- Languages All
Results 1 - 3 of 3 for 1xi8 (0.04 sec)
-
tensorflow/compiler/mlir/lite/experimental/tac/tests/raise-target-subgraphs.mlir
%0 = "tfl.pseudo_qconst"() {qtype = tensor<1x!quant.uniform<i8:f32, 0.003:-128>>, value = dense<127> : tensor<1xi8>} : () -> tensor<1x!quant.uniform<i8:f32, 0.003:-128>> %1 = "tfl.pseudo_qconst"() {qtype = tensor<1x!quant.uniform<i8:f32, 0.003:-128>>, value = dense<127> : tensor<1xi8>} : () -> tensor<1x!quant.uniform<i8:f32, 0.003:-128>>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 74.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/replace_cast_hacks_with_tf_xla_ops.mlir
%19 = "tf.BroadcastTo"(%4, %17) : (tensor<2x?x?xi8>, tensor<3xi64>) -> tensor<2x?x?xi8> %20 = "tf.BroadcastTo"(%9, %18) : (tensor<2x?x?xi8>, tensor<3xi64>) -> tensor<2x?x?xi8> %21 = "tf.XlaDotV2"(%19, %20) {dimension_numbers = "\22\01\00\1A\01\00\12\01\01\0A\01\02", precision_config = ""} : (tensor<2x?x?xi8>, tensor<2x?x?xi8>) -> tensor<2x?x?xi32> %22 = "tf.Cast"(%19) {Truncate = false} : (tensor<2x?x?xi8>) -> tensor<2x?x?xi32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 81K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/python/integration_test/quantize_model_test.py
) ) module_str = self._extract_first_xla_call_module_op( self._output_saved_model_path ) self.assertTrue( re.search('stablehlo.dot_general.*xi8>.*xi8>.*xi32>', module_str) ) # Run quantization the first time, calibration is expected to be skipped. output_saved_model_path_2 = self.create_tempdir('output2').full_path
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 14 06:31:57 UTC 2024 - 51.4K bytes - Viewed (0)