Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 4 of 4 for 8x16xf16 (0.19 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/quantization/tensorflow/tests/fallback_to_flex_ops_default.mlir 

    func.func @softmax(%arg0: tensor<8x16xf32>) -> tensor<8x16xf32> {
  %0 = "tf.Softmax"(%arg0) : (tensor<8x16xf32>) -> tensor<8x16xf32>
  func.return %0 : tensor<8x16xf32>
// CHECK: %[[CUSTOM_0:.*]] = "tfl.custom"(%arg0) <{custom_code = "FlexSoftmax", custom_option = #tfl<const_bytes : "0x07536F66746D617800161207536F66746D61781A002A070A0154120230013200000221191414042801">}> : (tensor<8x16xf32>) -> tensor<8x16xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 13.4K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/stablehlo/tests/passes/defer_activation_transpose.mlir 

      %1 = stablehlo.transpose %arg0, dims = [1, 0] : (tensor<16x8xf32>) -> tensor<8x16xf32>
  %2 = "stablehlo.reduce_window"(%1, %0) ({
  ^bb0(%arg1: tensor<f32>, %arg2: tensor<f32>):
      %3 = stablehlo.maximum %arg1, %arg2 : tensor<f32>
      stablehlo.return %3 : tensor<f32>
  }) {window_dimensions = array<i64: 2, 2>, window_strides = array<i64: 2, 2>} : (tensor<8x16xf32>, tensor<f32>) -> tensor<4x8xf32>
  return %2 : tensor<4x8xf32>
}
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 18 20:32:46 UTC 2024
    - 14.6K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/stablehlo/tests/compose-uniform-quantized-type.mlir 

    // CHECK: %[[UQ_1:.*]] = stablehlo.uniform_quantize %[[ARG_1]] : (tensor<8x16x4xf32>) -> tensor<8x16x4x!quant.uniform<i8:f32, 2.500000e+00>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 14 17:10:32 UTC 2024
    - 37K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/prepare-quantize-dynamic-range.mlir 

    // Float16-DAG: %[[b:.*]] = arith.constant dense<0.000000e+00> : tensor<16xf16>
// Float16-DAG: %[[const:.*]] = "tfl.no_value"() <{value}> : () -> none
// Float16-DAG: %[[dq_w:.*]] = "tfl.dequantize"(%[[w]]) : (tensor<3x3x3x8x16xf16>) -> tensor<3x3x3x8x16xf32>
// Float16-DAG: %[[dq_b:.*]] = "tfl.dequantize"(%[[b]]) : (tensor<16xf16>) -> tensor<16xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 38.2K bytes
    - Viewed (0)
Back to top