saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-02 03:55:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

remove const cast for DLManagedTensor (#20015)

Browse source 
### Description
<!-- Describe your changes. -->
Removing const_cast as it might lead to unknown behavior. Specifying
DLMangedTensor as a const doesn't seem to be necessary and I have tested
this by running torch_ort.configure. Not sure what other tests which
needs to be done. Background can be found in this
[PR](https://github.com/microsoft/onnxruntime/pull/19982)


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This commit is contained in:
Abhishek Jindal 2024-03-22 10:39:19 -07:00 committed by GitHub
parent 2bc29244b4
commit 7e84ba0ea3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
onnxruntime/python/torch_cpp_extensions/aten_op_executor/aten_op_executor.cc
View file

@ -36,7 +36,7 @@ struct ATenOperator {
size_t return_size;
std::vector<c10::TypeKind> ret_kinds;
c10::IValue ToIValueArgument(const DLManagedTensor* dlpack, size_t index) const {
c10::IValue ToIValueArgument(DLManagedTensor* dlpack, size_t index) const {
TORCH_INTERNAL_ASSERT(index < argument_size);
bool is_optional = is_optional_arguments[index];
TORCH_INTERNAL_ASSERT(dlpack || is_optional || default_values[index] ||
@ -57,7 +57,7 @@ struct ATenOperator {
c10::IValue i_value;
// Create the torch tensor from this DLPack no matter we need it or not below,
// so that the dlpack's deleter will be triggered when torch tensor is out of scope.
at::Tensor tensor = at::fromDLPack(const_cast<DLManagedTensor*>(dlpack));
at::Tensor tensor = at::fromDLPack(dlpack);
switch (elem_kinds[index]) {
case c10::TypeKind::TensorType: {
i_value = is_optional ? c10::IValue(c10::optional<at::Tensor>(tensor)) : c10::IValue(tensor);