CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

common, server : surface min_keep as its own parameter (#5567)

Browse Source 
* Feature - surface min_keep as its own parameter

* Updated README with min_keep param
This commit is contained in:
Robey Holderith
2024-02-18 11:11:16 -08:00
committed by GitHub
parent c145f8a132
commit 5ee99c32f5
6 changed files with 14 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@@ -548,6 +548,7 @@ struct llama_server_context
slot->params.seed = json_value(data, "seed", default_params.seed);
slot->sparams.grammar = json_value(data, "grammar", default_sparams.grammar);
slot->sparams.n_probs = json_value(data, "n_probs", default_sparams.n_probs);
slot->sparams.min_keep = json_value(data, "min_keep", default_sparams.min_keep);
if (slot->n_predict > 0 && slot->params.n_predict > slot->n_predict) {
// Might be better to reject the request with a 400 ?
@@ -1093,6 +1094,7 @@ struct llama_server_context
{"stream", slot.params.stream},
{"logit_bias", slot.sparams.logit_bias},
{"n_probs", slot.sparams.n_probs},
{"min_keep", slot.sparams.min_keep},
{"grammar", slot.sparams.grammar},
{"samplers", samplers_sequence}
};