- Sort Score
- Result 10 results
- Languages All
Results 1 - 3 of 3 for graph_in_ (2.23 sec)
-
tensorflow/compiler/mlir/lite/transforms/passes.h
// so redudant ones may be grouped and removed. std::unique_ptr<OperationPass<ModuleOp>> CreatePushTransposeThroughEwisePass(); // Creates a pass that brings operations into the same order as graph_info.cc. std::unique_ptr<OperationPass<func::FuncOp>> CreatePartitionedTopologicalSortPass(); #define GEN_PASS_DECL_DEFAULTQUANTPARAMSPASS #define GEN_PASS_DECL_DENSETOSPARSEPASS #define GEN_PASS_DECL_LEGALIZETFPASS
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 07 21:29:34 UTC 2024 - 10.9K bytes - Viewed (0) -
src/internal/trace/traceviewer/mmu.go
// Copyright 2023 The Go Authors. All rights reserved. // Use of this source code is governed by a BSD-style // license that can be found in the LICENSE file. // Minimum mutator utilization (MMU) graphing. // TODO: // // In worst window list, show break-down of GC utilization sources // (STW, assist, etc). Probably requires a different MutatorUtil // representation. // // When a window size is selected, show a second plot of the mutator
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Tue Nov 21 21:29:53 UTC 2023 - 13K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/passes.td
executed by the Flex delegate will be followed by another Flex delegated operator, if possible. The reordering uses the same greedy procedure that is executed at runtime (in tensorflow/lite/graph_info.cc.) This allows us to have an IR of the model that is in the same execution order as it will have at runtime (provided Flex is the only delegate present); this
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 20:30:06 UTC 2024 - 22.6K bytes - Viewed (0)