- Sort Score
- Result 10 results
- Languages All
Results 1 - 2 of 2 for GetQuantDequantCost (2.56 sec)
-
tensorflow/compiler/mlir/lite/experimental/tac/transforms/cost_model.cc
GetTransferredTensorBytes(from_graph, to_graph); return to_hardware->GetHardwareSwitchingCost(from_hardware, total_size_transferred); } float GetQuantDequantCost(InferenceType from_inference_type, InferenceType to_inference_type, func::CallOp from_graph, func::CallOp to_graph) { // Same inference type, no dequant/quant happens.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 7.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/transforms/pick_subgraphs.cc
current_inference_device_type.hardware, input_subgraph->call, current_graph_call); float quant_dequant_cost = GetQuantDequantCost(input_inference_device_type.inference_type, current_inference_device_type.inference_type, input_subgraph->call, current_graph_call); float summed_cost =
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Nov 24 15:10:02 UTC 2022 - 19.7K bytes - Viewed (0)