Skip to content

Make type of logits a template parameter #14921

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
Oct 9, 2025
Merged

Make type of logits a template parameter #14921

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
6 changes: 3 additions & 3 deletions examples/models/llama/runner/static_attention_io_manager.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -586,12 +586,12 @@ class StaticAttentionIOManager {
* of the prompt and method's input length. Returns the position in the output
* that corresponds to the end of the prompt during the last inference.
*/
template <typename TokenT>
template <typename TokenT, typename LogitT>
size_t prefill(
executorch::runtime::Span<TokenT> tokens,
executorch::runtime::Span<TokenT> input_buffer,
executorch::runtime::Method& method,
std::function<void(executorch::runtime::Span<const float>)>
std::function<void(executorch::runtime::Span<const LogitT>)>
logits_callback = nullptr) {
ET_LOG(Info, "Prefilling at position %zu", input_pos_);
size_t input_len = input_buffer.size();
Expand Down Expand Up @@ -619,7 +619,7 @@ class StaticAttentionIOManager {
batch_len);
if (logits_callback) {
auto logits_tensor = method.get_output(0).toTensor();
auto* logits = logits_tensor.const_data_ptr<float>();
auto* logits = logits_tensor.const_data_ptr<LogitT>();
logits_callback(executorch::runtime::Span(
logits,
logits + batch_len * logits_tensor.size(logits_tensor.dim() - 1)));
Expand Down
Loading