wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

server: allow API calls to set a lower thinking budget if a global budget is set

Browse Source
This commit is contained in:
Ruben Ortlam
2026-05-30 08:51:06 +02:00
parent 1738129bee
commit 926b94a1bc
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-common.cpp
+5 -2
View File
@@ -1123,8 +1123,11 @@ json oaicompat_chat_params_parse(
// Reasoning budget: pass parameters through to sampling layer
{
int reasoning_budget = opt.reasoning_budget;
if (reasoning_budget == -1 && body.contains("thinking_budget_tokens")) {
reasoning_budget = json_value(body, "thinking_budget_tokens", -1);
if (body.contains("thinking_budget_tokens")) {
int req_budget = json_value(body, "thinking_budget_tokens", -1);
if (reasoning_budget == -1 || (req_budget != -1 && req_budget < reasoning_budget)) {
reasoning_budget = req_budget;
}
}
if (!chat_params.thinking_end_tag.empty()) {