tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Server: Don't ignore llama.cpp params (#8754)

Browse Source 
* Don't ignore llama.cpp params

* Add fallback for max_tokens
This commit is contained in:
ardfork
2024-08-04 18:16:23 +00:00
committed by GitHub
parent ecf6b7f23e
commit 978ba3d83d
2 changed files with 1 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -900,7 +900,7 @@ struct server_context {
slot.params.stream = json_value(data, "stream", false);
slot.params.cache_prompt = json_value(data, "cache_prompt", false);
slot.params.n_predict = json_value(data, "n_predict", default_params.n_predict);
slot.params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", default_params.n_predict));
slot.sparams.top_k = json_value(data, "top_k", default_sparams.top_k);
slot.sparams.top_p = json_value(data, "top_p", default_sparams.top_p);
slot.sparams.min_p = json_value(data, "min_p", default_sparams.min_p);