Skip to content
This repository was archived by the owner on Sep 10, 2025. It is now read-only.
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion .pins/et-pin.txt
Original file line number Diff line number Diff line change
@@ -1 +1 @@
ff4e9edc55c86953ae33dbbaaacab8c9949dcb74
172574a6be5910a4609e4ed1bef2b6b8475ddb3d
4 changes: 2 additions & 2 deletions runner/run.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -203,9 +203,9 @@ float* forward(Transformer* transformer, int token, int pos) {
.to(torch::kCPU);
auto logits = result[0].data_ptr();
#else // __ET_MODEL__
ManagedTensor pos_managed(pos_buffer, sizeof(int64_t), {1}, ScalarType::Long);
ManagedTensor pos_managed(pos_buffer, {1}, ScalarType::Long);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why update this? Does new ET have new api interface?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yup ET got rid of it months ago

ManagedTensor tokens_managed(
token_buffer, sizeof(int64_t), {1, 1}, ScalarType::Long);
token_buffer, {1, 1}, ScalarType::Long);
std::vector<EValue> inputs;
auto tmp1 = EValue(tokens_managed.get_aliasing_tensor());
auto tmp2 = EValue(pos_managed.get_aliasing_tensor());
Expand Down