happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server : support max_completion_tokens request property (#19831) 

"max_tokens" is deprectated in favor of "max_completion_tokens" which
sets the upper bound for reasoning+output token.

Closes: #13700
This commit is contained in:
Radoslav Gerganov 2026-02-24 10:30:00 +02:00 committed by GitHub
parent aa6f918c1c
commit c830f99cfa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/server-task.cpp
View File

@ -204,7 +204,8 @@ task_params server_task::params_from_json_cmpl(
params.cache_prompt = json_value(data, "cache_prompt", defaults.cache_prompt);
params.return_tokens = json_value(data, "return_tokens", false);
params.return_progress = json_value(data, "return_progress", false);
params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", defaults.n_predict));
auto max_tokens = json_value(data, "max_tokens", defaults.n_predict);
params.n_predict = json_value(data, "n_predict", json_value(data, "max_completion_tokens", max_tokens));
params.n_indent = json_value(data, "n_indent", defaults.n_indent);
params.n_keep = json_value(data, "n_keep", defaults.n_keep);
params.n_discard = json_value(data, "n_discard", defaults.n_discard);