Skip to content

server : fix "can batch with" bug #17263

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
Nov 14, 2025
+10 −6
Merged

server : fix "can batch with" bug #17263

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
16 changes: 10 additions & 6 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3591,13 +3591,13 @@ struct server_context {
// next, batch any pending prompts without exceeding n_batch
if (params_base.cont_batching || batch.n_tokens == 0) {
for (auto & slot : slots) {
if (!slot.is_processing()) {
continue;
}

// check if we can batch this slot with the previous one
if (slot.is_processing()) {
if (!slot_batched) {
slot_batched = &slot;
} else if (!slot_batched->can_batch_with(slot)) {
continue;
}
if (slot_batched && !slot_batched->can_batch_with(slot)) {
continue;
}

// this slot still has a prompt to be processed
Expand Down Expand Up @@ -4028,6 +4028,10 @@ struct server_context {
}
}

if (!slot_batched) {
slot_batched = &slot;
}

if (batch.n_tokens >= n_batch) {
break;
}
Expand Down
Loading