- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 10 for PartitionedCall (0.23 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize_composit_functions_debugging.mlir
// TF-DAG: %[[pc_0:.*]] = "tf.PartitionedCall"(%arg0, %[[cst_4]], %[[cst_5]]) <{config = "", config_proto = "", executor_type = "", f = @quantize_i8} // TF-DAG: %[[pc_1:.*]] = "tf.PartitionedCall"(%[[pc_0]], %[[cst_2]], %[[cst_4]], %[[cst_5]], %[[cst_8]], %[[cst_9]], %[[cst_6]], %[[cst_5]]) <{config = "", config_proto = "", executor_type = "", f = @quantized_matmul_fn_1}
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Nov 06 01:23:21 UTC 2023 - 80.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/replace_cast_hacks_with_tf_xla_ops.mlir
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/tensorflow/tests/tensor_array_ops_decomposition.mlir
: (tensor<!tf_type.resource>) -> tensor<!tf_type.resource> // CHECK: "tf.PartitionedCall"(%[[VAR]], %[[GVAR1]], %[[GVAR2]]) // CHECK-SAME: f = @callee_tensorarray_decomposed %call2 = "tf.PartitionedCall"(%call) {f = @callee, config = "", config_proto = "", executor_type = ""} : (tensor<!tf_type.resource>) -> tensor<!tf_type.resource>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 49K bytes - Viewed (0) -
tensorflow/compiler/jit/mark_for_compilation_pass.cc
using jit::DeviceId; using jit::DeviceSet; // The clusters we create here are eventually lowered into an // _XlaCompile/_XlaRun pair with a TF executor "fallback" that uses the // PartitionedCall op to execute the cluster in the regular graph executor if // need be. PartitionedCall, however, reruns the entire TF graph optimization // pipeline over the cluster which includes this mark for compilation pass. To
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 12:19:41 UTC 2024 - 85.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/resource_op_lifting.mlir
// CHECK: %[[PC0:.*]] = "tf.PartitionedCall"(%[[CONST]], %[[READ]], %[[CONST]]) // CHECK-SAME: f = @callee_resource_lifted %3 = "tf.PartitionedCall"(%1, %0, %1) {f = @callee, config = "", config_proto = "", executor_type = ""} : (tensor<f32>, tensor<*x!tf_type.resource<tensor<f32>>>, tensor<f32>) -> tensor<f32> // CHECK: %[[PC1:.*]] = "tf.PartitionedCall"(%[[CONST]], %[[READ]], %[[CONST]])
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 74K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/quantize_composite_functions.cc
for (auto current_type : result_types) { if (mlir::dyn_cast<TensorType>(current_type).getElementType().isF32()) return true; } return false; } // Unwraps quantization parameters of PartitionedCall ops with quantized // input/outputs that are created from QuantizePass. class QuantizeFunctionPattern : public mlir::OpRewritePattern<TF::PartitionedCallOp> { public:
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 54.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/g3doc/_includes/tf_passes.md
``` `_XlaMustCompile=true` in the following code ```mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Aug 02 02:26:39 UTC 2023 - 96.4K bytes - Viewed (0) -
tensorflow/compiler/jit/mark_for_compilation_pass_test.cc
NameAttrList b_name_attr; b_name_attr.set_name("CompilableFn"); ops::PartitionedCall b(root.WithOpName("B"), {a, a}, {DT_FLOAT}, b_name_attr); NameAttrList c_name_attr; c_name_attr.set_name("UncompilableFn"); ops::PartitionedCall c(root.WithOpName("C"), {a}, {DT_FLOAT}, c_name_attr); Output d = ops::Add(root.WithOpName("D"), b.output.front(), c.output.front());
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 14 10:11:10 UTC 2024 - 79.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfrt/tests/mlrt/while_to_map_fn.mlir
func.func @serving_default(%arg0: tensor<?xf32> {tf.device = "/job:localhost/replica:0/task:0/device:CPU:0"}) -> tensor<3xf32> attributes {tf.entry_function = {control_outputs = "", inputs = "serving_default_input:0", outputs = "PartitionedCall:0"}} { %cst = "tf.Const"() {device = "/job:localhost/replica:0/task:0/device:CPU:0", value = dense<0> : tensor<i32>} : () -> tensor<i32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 23 06:40:22 UTC 2024 - 68.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_ops.td
The LegacyCall operation represents a direct call to a function that is within the same symbol scope as the call and is mapped to a GraphDef node with the function name as the op name. Unlike a PartitionedCall which represents asynchronously executing a function across multiple devices, a LegacyCall ignores specification for ops in the attached function and instead executes it on the device assigned to this op.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 04:08:35 UTC 2024 - 90.5K bytes - Viewed (0)