[IREE EP][Importer] Fix IR import for onnx.ConstantOfShape #11
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
vinayakdsci
requested review from
kumardeepakamd,
stellaraccident,
Shukla-Gaurav and
zjgarvey
kumardeepakamd
approved these changes
Sep 23, 2024
onnxruntime/core/providers/iree/compiler/torch-mlir-import-onnx/OnnxImporter.cpp
Outdated
Show resolved
Hide resolved
onnxruntime/core/providers/iree/compiler/torch-mlir-import-onnx/OnnxImporter.cpp
Outdated
Show resolved
Hide resolved
onnxruntime/core/providers/iree/compiler/torch-mlir-import-onnx/OnnxImporter.cpp
Outdated
Show resolved
Hide resolved
onnxruntime/core/providers/iree/compiler/torch-mlir-import-onnx/OnnxImporter.cpp
Outdated
Show resolved
Hide resolved
|
Thanks for the review, @kumardeepakamd and @Shukla-Gaurav! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes the IR generation for
onnx.ConstantOfShapeop. Earlier, the op would segfault, due to absence of data intensor_proto.<type>_data(). The importer now directly uses raw data from the tensor proto to generate a splat tensor.Also, now the output of the op is stored in
nv_mapwith the name of the output, rather than the name of the node, so that there is no "Non topologically produced ONNX input node" error, when the output is consumed later in the IR.