ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

set cache_prompt default to true (#465)

Browse Source
This commit is contained in:
saood06
2025-05-28 00:18:25 -05:00
committed by GitHub
parent 6989ca0249
commit ccc00a4a56
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@@ -112,7 +112,7 @@ struct server_task_multi {
struct slot_params {
bool stream = true;
bool cache_prompt = false; // remember the prompt to avoid reprocessing all prompt
bool cache_prompt = true; // remember the prompt to avoid reprocessing all prompt
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_discard = 0; // number of tokens after n_keep that may be discarded when shifting context, 0 defaults to half
@@ -905,7 +905,7 @@ struct server_context {
}
slot.params.stream = json_value(data, "stream", false);
slot.params.cache_prompt = json_value(data, "cache_prompt", false);
slot.params.cache_prompt = json_value(data, "cache_prompt", true);
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);