wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 36 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 authored and GitHub committed 2024-08-04 20:16:23 +02:00
1 parent ecf6b7f23e
commit 978ba3d83d
2 files changed
+1 -19
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/server/server.cpp
+1 -1
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);