Search Options

Results per page
Sort
Preferred Languages
Advance

Results 21 - 30 of 111 for I8 (0.26 sec)

  2. github.com/tensorflow/tensorflow

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

    // CHECK: %[[QUANT_ARG:.*]] = stablehlo.uniform_quantize %[[ARG]] : (tensor<1x3x3x4xf32>) -> tensor<1x3x3x4x!quant.uniform<i8:f32, {{.*}}>>
// CHECK: %[[CONV:.*]] = stablehlo.convolution(%[[QUANT_ARG]], %[[FILTER]]) {{.*}} : (tensor<1x3x3x4x!quant.uniform<i8:f32, {{.*}}>>, tensor<3x3x4x4x!quant.uniform<i8:f32:3, {{.*}}>>) -> tensor<1x3x3x4x!quant.uniform<i8:f32, {{.*}}>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 14 17:10:32 UTC 2024
    - 37K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize.mlir 

      %dq_input= "quantfork.dcast"(%q_input) : (tensor<1x3x4x3x!quant.uniform<i8:f32, 0.58810077742034317:-128>>) -> tensor<1x3x4x3xf32>
  %q_weight = "quantfork.qcast"(%weight) : (tensor<2x3x3x2xf32>) -> tensor<2x3x3x2x!quant.uniform<i8:f32, 0.074855112561992565:-1>>
  %dq_weight = "quantfork.dcast"(%q_weight) : (tensor<2x3x3x2x!quant.uniform<i8:f32, 0.074855112561992565:-1>>) -> tensor<2x3x3x2xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 08 19:32:28 UTC 2024
    - 6.4K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/experimental/tac/tests/fold-constants-to-subgraph.mlir 

      func.return %2 : tensor<384x128x!quant.uniform<i8:f32, 0.09:-4>>
}

// PARTIAL-LABEL: @quantization_test
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 10.5K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

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

      %requant = stablehlo.uniform_quantize %conv : (tensor<1x3x4x2x!quant.uniform<i32:f32, 5.8949912267181218E-5>>) -> tensor<1x3x4x2x!quant.uniform<i8:f32, 0.045673100153605144:-62>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Feb 08 22:40:14 UTC 2024
    - 2.6K bytes
    - Viewed (0)
  6. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/experimental/tac/tests/get-alternative-subgraph.mlir 

      func.return %5 : tensor<1x384x128x!quant.uniform<i8:f32, 0.3:-3>>
}
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 20.1K bytes
    - Viewed (0)
  7. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/tensorflow_to_stablehlo/tests/test_tf_to_stablehlo.mlir 

    // CHECK: %[[BITCAST_CONVERT_0:.*]] = stablehlo.bitcast_convert %[[UQ]] : (tensor<1x!quant.uniform<i8:f32, 1.000000e+00:3>>) -> tensor<1xi8>
// CHECK: %[[BITCAST_CONVERT_1:.*]] = stablehlo.bitcast_convert %[[BITCAST_CONVERT_0]] : (tensor<1xi8>) -> tensor<1x!quant.uniform<i8:f32, 1.000000e+00:3>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 21 22:58:42 UTC 2024
    - 1.5K bytes
    - Viewed (0)
  8. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/tensorflow/transforms/host_runtime/runtime_passes.td 

            %2 = "tf.TPUExecute"(%arg0, %0#1) : (tensor<i8>, tensor<3x!tf_type.string>) -> tensor<i8>
        tf_device.return %2 : tensor<i8>
      }) {device = "/job:worker/replica:0/task:0/device:TPU:0"} : () -> tensor<i8>
      return
    }
    ```

    A replicated `tf_device.cluster_func`:

    ```mlir
    func @tf_tpu_rewrite(%arg0: tensor<i8>, %arg1: tensor<i8>) {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed Jan 10 18:58:57 UTC 2024
    - 10.7K bytes
    - Viewed (0)
  9. github.com/tensorflow/tensorflow

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

    // CHECK: %[[dq_w:.*]] = "tfl.dequantize"(%[[q_w]]) : (tensor<64x3x3x3x!quant.uniform<i8<-127:127>:f32, 1.000000e+00>>) -> tensor<64x3x3x3xf32>
// CHECK: %[[emb:.*]] = "tfl.gather"(%[[dq_w]], %arg0)
// CHECK: return %[[emb:.*]]

// PerTensor: %[[q_w:.*]] = "tfl.pseudo_qconst"() <{qtype = tensor<64x3x3x3x!quant.uniform<i8<-127:127>:f32, 1.000000e+00>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 23 21:09:00 UTC 2024
    - 23.2K bytes
    - Viewed (0)
  10. github.com/tensorflow/tensorflow

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

      %1 = "quantfork.qcast"(%0) : (tensor<8xf32>) -> tensor<8x!quant.uniform<i8:f32, 1.000000e+00:-128>>
  func.return %1 : tensor<8x!quant.uniform<i8:f32, 1.000000e+00:-128>>

// CHECK:  %0 = "tf.FakeQuantWithMinMaxVars"(%arg0, %cst, %cst_0) <{narrow_range = false, num_bits = 5 : i64}>
// CHECK:  %1 = "quantfork.qcast"(%0) : (tensor<8xf32>) -> tensor<8x!quant.uniform<i8:f32, 1.000000e+00:-128>>
// CHECK:  return %1
}
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Mon Oct 30 06:52:55 UTC 2023
    - 9.5K bytes
    - Viewed (0)
  11. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir/lstm.mlir 

    // CHECK: }) : (tensor<1x528x!quant.uniform<i8:f32, 0.037248000502586365:-19>>, tensor<2048x528x!quant.uniform<i8:f32, 0.059801999479532242>>, tensor<2048x528x!quant.uniform<i8:f32, 0.031925998628139496>>, tensor<2048x528x!quant.uniform<i8:f32, 0.056272000074386597>>, tensor<2048x528x!quant.uniform<i8:f32, 0.063763998448848724>>, tensor<2048x640x!quant.uniform<i8:f32, 0.013358999975025654>>, tensor<2048x640x!quant.uniform<i8:f32, 0.022830000147223473>>, tensor<2048x640x!quant.uniform<i8:f32,...
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 20.4K bytes
    - Viewed (0)
Back to top