tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

speculative : update default params (#11954)

Browse Source 
* speculative : update default params

* speculative : do not discard the last drafted token
This commit is contained in:
Georgi Gerganov
2025-02-19 13:29:42 +02:00
committed by GitHub
parent 9626d9351a
commit abd4d0bc4f
4 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -274,7 +274,7 @@ struct server_task {
params.speculative.p_min = json_value(data, "speculative.p_min", defaults.speculative.p_min);
params.speculative.n_min = std::min(params.speculative.n_max, params.speculative.n_min);
params.speculative.n_min = std::max(params.speculative.n_min, 2);
params.speculative.n_min = std::max(params.speculative.n_min, 0);
params.speculative.n_max = std::max(params.speculative.n_max, 0);
// Use OpenAI API logprobs only if n_probs wasn't provided