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: Enable setting default sampling parameters via command-line (#8402)

Browse Source 
* Load server sampling parameters from the server context by default.

* Wordsmithing comment
This commit is contained in:
Clint Herron
2024-07-09 18:26:40 -04:00
committed by GitHub
parent fd560fe680
commit a59f8fdc85
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; // Sampling parameter defaults are loaded from the global server context (but individual requests can still override them)
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) {