tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-16 05:02:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : allow specifying reasoning_format in HTTP request (#15238)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-08-11 14:48:41 +02:00
committed by GitHub
parent 27093afe78
commit 53d0a12658
7 changed files with 28 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
common/arg.cpp
View File

@@ -2949,11 +2949,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"- deepseek: puts thoughts in `message.reasoning_content` (except in streaming mode, which behaves as `none`)\n"
"(default: auto)",
[](common_params & params, const std::string & value) {
/**/ if (value == "deepseek") { params.reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK; }
else if (value == "deepseek-legacy") { params.reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK_LEGACY; }
else if (value == "none") { params.reasoning_format = COMMON_REASONING_FORMAT_NONE; }
else if (value == "auto") { params.reasoning_format = COMMON_REASONING_FORMAT_AUTO; }
else { throw std::invalid_argument("invalid value"); }
params.reasoning_format = common_reasoning_format_from_name(value);
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_MAIN}).set_env("LLAMA_ARG_THINK"));
add_opt(common_arg(