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 : 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
1 changed files with 1 additions and 2 deletions
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.command = SLOT_COMMAND_NONE;
slot.release();
slot.print_timings();
send_final_response(slot);
send_error(slot, "input is too large to process. increase the physical batch size", ERROR_TYPE_SERVER);
continue;
}
} else {