Skip to content

server : add kill switch when server is stuck #20277

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
ggerganov merged 1 commit into from
Mar 9, 2026
Merged

server : add kill switch when server is stuck #20277

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
9 changes: 8 additions & 1 deletion tools/server/server-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -562,14 +562,15 @@ struct server_context_impl {

llama_model_ptr model_dft;

bool add_bos_token = true;
bool add_bos_token = true;

int32_t n_ctx; // total context for all clients / slots

// slots / clients
std::vector<server_slot> slots;

int slots_debug = 0;
int n_empty_consequtive = 0;
Copy link
Contributor

@aviallon aviallon Mar 9, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ggerganov
Did you mean consecutive?


std::unique_ptr<server_prompt_cache> prompt_cache;

Expand Down Expand Up @@ -2628,6 +2629,12 @@ struct server_context_impl {

if (batch.n_tokens == 0) {
SRV_WRN("%s", "no tokens to decode\n");

if (++n_empty_consequtive > 3) {
GGML_ABORT("fatal error - please provide logs and repro in %s\n", "https://github.com/ggml-org/llama.cpp/pull/20277");
}
} else {
n_empty_consequtive = 0;
}

int32_t i_next = 0;
Expand Down
Loading