Skip to content

server : infill gen ends on new line #12254

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
Mar 7, 2025
Merged

server : infill gen ends on new line #12254

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
18 changes: 9 additions & 9 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1312,7 +1312,7 @@ struct server_slot {
return task_type == SERVER_TASK_TYPE_EMBEDDING || task_type == SERVER_TASK_TYPE_RERANK;
}

bool can_batch_with(server_slot & other_slot) {
bool can_batch_with(server_slot & other_slot) const {
return is_non_causal() == other_slot.is_non_causal()
&& are_lora_equal(lora, other_slot.lora);
}
Expand Down Expand Up @@ -2157,14 +2157,6 @@ struct server_context {
}

if (slot.has_new_line) {
// if we have already seen a new line, we stop after a certain time limit
if (slot.params.t_max_predict_ms > 0 && (ggml_time_us() - slot.t_start_generation > 1000.0f*slot.params.t_max_predict_ms)) {
slot.stop = STOP_TYPE_LIMIT;
slot.has_next_token = false;

SLT_DBG(slot, "stopped by time limit, n_decoded = %d, t_max_predict_ms = %d ms\n", slot.n_decoded, (int) slot.params.t_max_predict_ms);
}

// require that each new line has a whitespace prefix (i.e. indentation) of at least slot.params.n_indent
if (slot.params.n_indent > 0) {
// check the current indentation
Expand Down Expand Up @@ -2203,6 +2195,14 @@ struct server_context {
// check if there is a new line in the generated text
if (result.text_to_send.find('\n') != std::string::npos) {
slot.has_new_line = true;

// if we have seen a new line, we stop after a certain time limit, but only upon another new line
if (slot.params.t_max_predict_ms > 0 && (ggml_time_us() - slot.t_start_generation > 1000.0f*slot.params.t_max_predict_ms)) {
slot.stop = STOP_TYPE_LIMIT;
slot.has_next_token = false;

SLT_DBG(slot, "stopped by time limit, n_decoded = %d, t_max_predict_ms = %d ms\n", slot.n_decoded, (int) slot.params.t_max_predict_ms);
}
}

// if context shift is disabled, we stop when it reaches the context limit
Expand Down
Loading