nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 22 Packages Projects Releases Wiki Activity

server : fix reasoning budget WebUI precedence over model.ini (#24517)

Browse Source 
When reasoning-budget is set in model.ini, the per-request
thinking_budget_tokens from the WebUI was ignored because the
model.ini value took unconditional precedence.

Swap the precedence so the WebUI per-request value is checked
first, with the model.ini value serving as a fallback default.

Assisted-by: pi:llama.cpp/Qwen3.6-27B
This commit is contained in:
Georgi Gerganov
2026-06-12 17:59:56 +03:00
committed by GitHub
parent 3e7bd4f39a
commit ebc10770ac
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-common.cpp
+3 -3
View File
@@ -1126,9 +1126,9 @@ json oaicompat_chat_params_parse(
// Reasoning budget: pass parameters through to sampling layer // Reasoning budget: pass parameters through to sampling layer
{ {
int reasoning_budget = opt.reasoning_budget; int reasoning_budget = json_value(body, "thinking_budget_tokens", -1);
if (reasoning_budget == -1 && body.contains("thinking_budget_tokens")) { if (reasoning_budget == -1) {
reasoning_budget = json_value(body, "thinking_budget_tokens", -1); reasoning_budget = opt.reasoning_budget;
} }
if (!chat_params.thinking_end_tag.empty()) { if (!chat_params.thinking_end_tag.empty()) {