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

server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771)

Browse Source 
---------

Co-authored-by: ochafik <ochafik@google.com>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Olivier Chafik
2025-05-26 00:30:51 +01:00
committed by GitHub
parent 2f099b510f
commit e121edc432
12 changed files with 277 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/utils.hpp
View File

@@ -568,6 +568,7 @@ struct oaicompat_parser_options {
common_chat_templates * tmpls;
bool allow_image;
bool allow_audio;
bool enable_thinking = true;
};
// used by /chat/completions endpoint
@@ -733,6 +734,7 @@ static json oaicompat_chat_params_parse(
inputs.parallel_tool_calls = json_value(body, "parallel_tool_calls", false);
inputs.add_generation_prompt = json_value(body, "add_generation_prompt", true);
inputs.reasoning_format = opt.reasoning_format;
inputs.enable_thinking = opt.enable_thinking;
if (!inputs.tools.empty() && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE && body.contains("grammar")) {
throw std::runtime_error("Cannot use custom grammar constraints with tools.");
}