root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

server : return error on too large embedding input (#7389)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-05-20 08:56:05 +03:00 committed by GitHub
parent 2789baf480
commit e932094d58
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
examples/server/server.cpp
View File

@ -1981,8 +1981,7 @@ struct server_context {
slot.state = SLOT_STATE_PROCESSING; slot.state = SLOT_STATE_PROCESSING;
slot.command = SLOT_COMMAND_NONE; slot.command = SLOT_COMMAND_NONE;
slot.release(); slot.release();
slot.print_timings(); send_error(slot, "input is too large to process. increase the physical batch size", ERROR_TYPE_SERVER);
send_final_response(slot);
continue; continue;
} }
} else { } else {