Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 9 of 9 for 2x1024xi8 (0.15 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/propagate_quantize_type.mlir 

        %cst = "tf.Const"() {value = dense<127> : tensor<2x1024xi8>} : () -> tensor<2x1024xi8>
    %cst_0 = "tf.Const"() {value = dense<0.0157480314> : tensor<f32>} : () -> tensor<f32>
    %0 = "tf.Identity"(%cst) : (tensor<2x1024xi8>) -> tensor<2x1024xi8>
    %1 = "tf.Cast"(%0) {Truncate = false} : (tensor<2x1024xi8>) -> tensor<2x1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 6.6K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize_weights.mlir 

    // CHECK-LABEL: func @matmul
// CHECK-DAG: %[[W:.*]] = "tf.Const"() <{value = dense<127> : tensor<2x1024xi8>
// CHECK: %[[PRESERVE_W:.*]] = "tf.Identity"(%[[W]]) : (tensor<2x1024xi8>) -> tensor<2x1024xi8>
// CHECK: %[[DEQUANTIZED:.*]] = "tf.PartitionedCall"(%[[PRESERVE_W]]) <{config = "", config_proto = "", executor_type = "", f = @composite_dequantize_uniform}> : (tensor<2x1024xi8>) -> tensor<2x1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 42K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/replace_cast_hacks_with_tf_xla_ops.mlir 

        %4 = "tf.Cast"(%3) {Truncate = false, device = ""} : (tensor<1x1024xf32>) -> tensor<1x1024xi8>
    %5 = "tf.Cast"(%4) {Truncate = false, device = ""} : (tensor<1x1024xi8>) -> tensor<1x1024xi32>
    %6 = "tf.Sub"(%5, %cst_4) {device = ""} : (tensor<1x1024xi32>, tensor<i32>) -> tensor<1x1024xi32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 81K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize_drq.mlir 

    // CHECK: %[[q_cst:.*]] = "quantfork.qcast"(%[[cst]]) : (tensor<2x1024xf32>) -> tensor<2x1024x!quant.uniform<i8<-127:127>:f32, 3.9370078740157481E-9>>
// CHECK: %[[out:.*]] = "tf.PartitionedCall"([[ARG0:%arg[0-9]+]], %[[q_cst]]) <{config = "", config_proto = "", executor_type = "", f = @composite_matmul_fn}> {_tfl_quant_trait = "fully_quantizable"} : (tensor<1x2x2x3xf32>, tensor<2x1024x!quant.uniform<i8<-127:127>:f32, 3.9370078740157481E-9>>) -> tensor<*xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 08 19:32:28 UTC 2024
    - 1.6K bytes
    - Viewed (0)
  6. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/prepare_quantize_drq_per_channel.mlir 

    // CHECK-DAG: %[[CONST:.*]] = arith.constant dense<0.000000e+00> : tensor<2x1024xf32>
// CHECK: %0 = "quantfork.qcast"(%[[CONST]]) : (tensor<2x1024xf32>) -> tensor<2x1024x!quant.uniform<i8<-127:127>:f32, 3.9370078740157481E-9>>
// CHECK: %1 = "quantfork.dcast"(%0) : (tensor<2x1024x!quant.uniform<i8<-127:127>:f32, 3.9370078740157481E-9>>) -> tensor<2x1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 6.8K bytes
    - Viewed (0)
  7. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/prepare_quantize_drq.mlir 

    // CHECK-DAG: %[[CONST:.*]] = arith.constant dense<0.000000e+00> : tensor<2x1024xf32>
// CHECK: %0 = "quantfork.qcast"(%[[CONST]]) : (tensor<2x1024xf32>) -> tensor<2x1024x!quant.uniform<i8<-127:127>:f32, 3.9370078740157481E-9>>
// CHECK: %1 = "quantfork.dcast"(%0) : (tensor<2x1024x!quant.uniform<i8<-127:127>:f32, 3.9370078740157481E-9>>) -> tensor<2x1024xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 6.7K bytes
    - Viewed (0)
  8. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/stablehlo/tests/components/post_calibration_component.mlir 

    // Tests that the dot_general accepts i8 tensors and outputs an i32 tensor.
// Note: Argument quantization sequence omitted.
// CHECK: stablehlo.dot_general %{{.+}}, %{{.+}}, contracting_dims = [1] x [0] : (tensor<1x1024xi8>, tensor<1024x3xi8>) -> tensor<1x3xi32>

// Note: Result dequantization sequence omitted.
// CHECK: return %{{.+}} : tensor<1x3xf32>

// -----
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 01:09:50 UTC 2024
    - 6.7K bytes
    - Viewed (0)
  9. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/stablehlo/tests/legalize_hlo.mlir 

    // CHECK-SAME:                         %[[ARG_1:.*]]: tensor<?x?x1xi32>) -> tensor<?x?x1024xi8> {
// CHECK:            %[[VAL_0:.*]] = "tf.GatherNd"(%[[ARG_0]], %[[ARG_1]]) <{bad_indices_policy = ""}> : (tensor<256000x1024xi8>, tensor<?x?x1xi32>) -> tensor<?x?x1024xi8>
// CHECK:            return %[[VAL_0]] : tensor<?x?x1024xi8>
// CHECK:         }
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 29 07:26:59 UTC 2024
    - 340.2K bytes
    - Viewed (0)
  10. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/stablehlo/tests/uniform-quantized-stablehlo-to-tfl.mlir 

    // CHECK-NOT: stablehlo.dot_general
// CHECK: %[[QCONST_0:.+]] =  "tfl.pseudo_qconst"() <{qtype = tensor<3x1024x!quant.uniform<i8<-127:127>:f32:0, {2.000000e+00,2.000000e+00,2.000000e+00}>>, value = dense<1> : tensor<3x1024xi8>}> : () -> tensor<3x1024x!quant.uniform<i8<-127:127>:f32:0, {2.000000e+00,2.000000e+00,2.000000e+00}>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 14 17:10:32 UTC 2024
    - 106.2K bytes
    - Viewed (0)
Back to top