Skip to content

llama-server: friendlier error msg when ctx < input #18174

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
ngxson merged 3 commits into from
Dec 19, 2025
+17 −3
Merged

llama-server: friendlier error msg when ctx < input #18174

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
56c8222
llama-server: friendlier error msg when ctx < input
am17an Dec 15, 2025
c6417bd
llama-server: use string_format inline
am17an Dec 18, 2025
0141889
fix test
am17an Dec 19, 2025
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
20 changes: 17 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 @@ -1283,6 +1283,11 @@ struct server_context_impl {
queue_results.send(std::move(res));
}

template <typename T, typename... Args>
void send_error(const T & obj, const enum error_type type, const char * fmt, Args... args) {
send_error(obj, string_format(fmt, args...), type);
}

// if multimodal is enabled, send an error and return false
bool check_no_mtmd(const int id_task) {
if (mctx) {
Expand Down Expand Up @@ -1962,19 +1967,28 @@ struct server_context_impl {

if (!slot.can_split()) {
if (slot.task->n_tokens() > n_ubatch) {
send_error(slot, "input is too large to process. increase the physical batch size", ERROR_TYPE_SERVER);
send_error(slot, ERROR_TYPE_SERVER,
"input (%d tokens) is too large to process. increase the physical batch "
"size (current batch size: %d)",
slot.task->n_tokens(), n_ubatch);
slot.release();
continue;
}

if (slot.task->n_tokens() > slot.n_ctx) {
send_error(slot, "input is larger than the max context size. skipping", ERROR_TYPE_EXCEED_CONTEXT_SIZE);
send_error(
slot, ERROR_TYPE_EXCEED_CONTEXT_SIZE,
"input (%d tokens) is larger than the max context size (%d tokens). skipping",
slot.task->n_tokens(), slot.n_ctx);
slot.release();
continue;
}
} else {
if (slot.task->n_tokens() >= slot.n_ctx) {
send_error(slot, "the request exceeds the available context size, try increasing it", ERROR_TYPE_EXCEED_CONTEXT_SIZE);
send_error(
slot, ERROR_TYPE_EXCEED_CONTEXT_SIZE,
"request (%d tokens) exceeds available context size (%d tokens), try increasing it",
slot.task->n_tokens(), slot.n_ctx);
slot.release();
continue;
}
Expand Down
Loading