root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 13:30:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

fixed server 200 null response when context is exceeded

Browse Source
This commit is contained in:
VJHack 2024-09-20 14:54:08 -05:00
parent 2f2e4b35a6
commit 0cabcbe588
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/server/server.cpp
View File

@ -1464,11 +1464,10 @@ struct server_context {
std::vector<server_task_result> results(id_tasks.size());
for (size_t i = 0; i < id_tasks.size(); i++) {
server_task_result result = queue_results.recv(id_tasks);
if (result.error) {
error_handler(result.data);
cancel_tasks(id_tasks);
break;
return;
}
size_t idx = result.data["index"];
@ -1948,9 +1947,9 @@ struct server_context {
continue;
}
// context shift is disabled and prompt is too large - discard it
if (!params.ctx_shift && slot.n_prompt_tokens > slot.n_ctx ){
if (!params.ctx_shift && (slot.n_prompt_tokens > slot.n_ctx) ){
slot.release();
send_error(slot, "input is too large to process. enable context shift or increase the context length", ERROR_TYPE_SERVER);
send_error(slot, "Input is too large to process. Enable context shift or increase the context length", ERROR_TYPE_SERVER);
continue;
}