Skip to content

server : respect min-step when splitting prompt batches #25420

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
aldehir merged 1 commit into from
Jul 9, 2026
Merged

server : respect min-step when splitting prompt batches #25420

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
11 changes: 8 additions & 3 deletions tools/server/server-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3435,9 +3435,14 @@ struct server_context_impl {

slot.n_prompt_tokens_processed++;

// stop the prompt batch exactly before a user message
if (spans.is_user_start(slot.prompt.n_tokens())) {
break;
// break at the last user message, or at user messages at least min step past the last checkpoint
if (do_checkpoint && spans.is_user_start(slot.prompt.n_tokens())) {
const auto pos = slot.prompt.n_tokens();
const auto & checkpoints = slot.prompt.checkpoints;

if (pos == last_user_pos || checkpoints.empty() || pos > checkpoints.back().n_tokens + params_base.checkpoint_min_step) {
break;
}
}

// process the last few tokens of the prompt separately in order to allow for a checkpoint to be created.
Expand Down