Skip to content

server : improve error reporting #13680

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
May 21, 2025
Merged

server : improve error reporting #13680

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
29 changes: 22 additions & 7 deletions tools/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3361,14 +3361,29 @@ struct server_context {
metrics.on_decoded(slots);

if (ret != 0) {
if (n_batch == 1 || ret < 0) {
// if you get here, it means the KV cache is full - try increasing it via the context size
SRV_ERR("failed to decode the batch: KV cache is full - try increasing it via the context size, i = %d, n_batch = %d, ret = %d\n", i, n_batch, ret);
for (auto & slot : slots) {
slot.release();
send_error(slot, "Input prompt is too big compared to KV size. Please try increasing KV size.");
{
std::string err;

if (n_batch == 1 && ret == 1) {
err = "Context size has been exceeded.";
}

if (ret == -1) {
err = "Invalid input batch.";
}

if (ret < -1) {
err = "Compute error.";
}

if (!err.empty()) {
SRV_ERR("%s, i = %d, n_batch = %d, ret = %d\n", err.c_str(), i, n_batch, ret);
for (auto & slot : slots) {
slot.release();
send_error(slot, err);
}
break;
}
break; // break loop of n_batch
}

// retry with half the batch size to try to find a free slot in the KV cache
Expand Down
Loading