Skip to content

context : fix reorder logic #13267

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.

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
May 2, 2025
Merged
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
6 changes: 3 additions & 3 deletions src/llama-context.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1050,6 +1050,9 @@ int llama_context::decode(llama_batch & inp_batch) {
// finalize the batch processing
kv_guard.commit();

// set to total number of outputs in the batch, for use in llama_get_logits_ith
n_outputs = n_outputs_all;

// set output mappings
{
bool sorted_output = true;
Expand Down Expand Up @@ -1103,9 +1106,6 @@ int llama_context::decode(llama_batch & inp_batch) {
}
}

// set to total number of outputs in the batch, for use in llama_get_logits_ith
n_outputs = n_outputs_all;

// wait for the computation to finish (automatically done when obtaining the model output)
//synchronize();

Expand Down
Loading