- Sort Score
- Result 10 results
- Languages All
Results 1 - 2 of 2 for Edges (0.05 sec)
-
tensorflow/compiler/mlir/lite/flatbuffer_export.cc
// Populate the model control dependencies metadata entry. if (std::any_of( model_control_dependencies_.begin(), model_control_dependencies_.end(), [](const tflite::ControlEdges& edges) { return !edges.empty(); })) { metadata.push_back( BuildMetadata(tflite::kModelControlDependenciesMetadataKey, tflite::SerializeModelControlDependencies(
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 21:41:49 UTC 2024 - 164.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/tf_passes.td
let constructor = "TFTPU::CreateTPUColocateSplitsPass()"; let description = [{ It is beneficial for performance to assign a `Split` op to the same device as its predecessor. This is because the weight of cut edges is always minimized when the `Split` is with its predecessor. This colocation constraint will be used by the placer graph optimization to assign a device to the op.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 21:18:05 UTC 2024 - 99.6K bytes - Viewed (0)