vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Load server sampling parameters from the server context by default.

Browse source
This commit is contained in:
HanClinto 2024-07-09 16:50:45 -04:00
parent fd560fe680
commit 6cfa080950
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/server/server.cpp
View file

@ -884,7 +884,8 @@ struct server_context {
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_params default_params; slot_params default_params;
llama_sampling_params default_sparams; // Default sampling parameters are loaded from the server context unless overridden by individual requests
llama_sampling_params default_sparams = params.sparams;
auto & data = task.data; auto & data = task.data;
if (data.count("__oaicompat") != 0) { if (data.count("__oaicompat") != 0) {