Skip to content

Log dtype names on input dtype mismatch #7537

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 15, 2025
Merged

Log dtype names on input dtype mismatch #7537

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions runtime/executor/method.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -830,14 +830,14 @@ Method::set_input(const EValue& input_evalue, size_t input_idx) {
if (e.isTensor()) {
const auto& t_dst = e.toTensor();
const auto& t_src = input_evalue.toTensor();

ET_CHECK_OR_RETURN_ERROR(
t_dst.scalar_type() == t_src.scalar_type(),
InvalidArgument,
"The %zu-th input tensor's scalartype does not meet requirement: found %" PRId8
" but expected %" PRId8,
"Input %zu has unexpected scalar type: expected %s but was %s.",
input_idx,
static_cast<int8_t>(t_src.scalar_type()),
static_cast<int8_t>(t_dst.scalar_type()));
executorch::runtime::toString(t_dst.scalar_type()),
executorch::runtime::toString(t_src.scalar_type()));
// Reset the shape for the Method's input as the size of forwarded input
// tensor for shape dynamism. Also is a safety check if need memcpy.
Error err = resize_tensor(t_dst, t_src.sizes());
Expand Down
1 change: 1 addition & 0 deletions runtime/executor/targets.bzl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,7 @@ def define_common_targets():
"//executorch/runtime/core:evalue" + aten_suffix,
"//executorch/runtime/core:event_tracer" + aten_suffix,
"//executorch/runtime/core/exec_aten:lib" + aten_suffix,
"//executorch/runtime/core/exec_aten/util:scalar_type_util" + aten_suffix,
"//executorch/runtime/core/exec_aten/util:tensor_util" + aten_suffix,
"//executorch/runtime/kernel:kernel_runtime_context" + aten_suffix,
"//executorch/runtime/kernel:operator_registry",
Expand Down