CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* Fix DOS index bug

* Remove new APIs

* remove extra line

* Remove from API

* Add extra newline

* Update examples/server/server.cpp

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Ishaan Gandhi
2025-03-13 06:10:05 -04:00
committed by GitHub
parent f08f4b3187
commit 2048b5913d
1 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/server/server.cpp
View File

@@ -2040,6 +2040,18 @@ struct server_context {
return ret; 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) { bool launch_slot_with_task(server_slot & slot, const server_task & task) {
slot.reset(); slot.reset();
slot.id_task = task.id; slot.id_task = task.id;
@@ -2054,6 +2066,11 @@ struct server_context {
slot.lora = task.params.lora; 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()); 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) { if (slot.n_predict > 0 && slot.params.n_predict > slot.n_predict) {