Skip to content

server : fix crash when using verbose output with input tokens that are not in printable range (#12178) #12338

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 6 commits into from
Mar 13, 2025
Merged

server : fix crash when using verbose output with input tokens that are not in printable range (#12178) #12338

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d8485ad
Fix DOS index bug
ishaangandhi Mar 11, 2025
1320897
Remove new APIs
ishaangandhi Mar 11, 2025
761f4d9
remove extra line
ishaangandhi Mar 11, 2025
2e48a6d
Remove from API
ishaangandhi Mar 11, 2025
cc53039
Add extra newline
ishaangandhi Mar 11, 2025
1e14b14
Update examples/server/server.cpp
ngxson Mar 11, 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
17 changes: 17 additions & 0 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2040,6 +2040,18 @@ struct server_context {
return ret;
}

bool can_be_detokenized(const struct llama_context * ctx, const std::vector<llama_token> & tokens) {
const llama_model * model = llama_get_model(ctx);
const llama_vocab * vocab = llama_model_get_vocab(model);
const int32_t n_vocab = llama_vocab_n_tokens(vocab);
for (const auto & token : tokens) {
if (token < 0 || token >= n_vocab) {
return false;
}
}
return true;
}

bool launch_slot_with_task(server_slot & slot, const server_task & task) {
slot.reset();
slot.id_task = task.id;
Expand All @@ -2054,6 +2066,11 @@ struct server_context {
slot.lora = task.params.lora;
}

bool can_detokenize = can_be_detokenized(ctx, slot.prompt_tokens);
if (!can_detokenize) {
send_error(task, "Prompt contains invalid tokens", ERROR_TYPE_INVALID_REQUEST);
return false;
}
SLT_DBG(slot, "launching slot : %s\n", safe_json_to_str(slot.to_json()).c_str());

if (slot.n_predict > 0 && slot.params.n_predict > slot.n_predict) {
Expand Down
Loading