jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

server : hint preserve_thinking when supported by chat template

Browse Source 
Print a hint to enable preserve_thinking kwarg when the template supports it.

ref: https://docs.z.ai/guides/capabilities/thinking-mode#preserved-thinking
Assisted-by: pi:llama.cpp/Qwen3.6-27B
This commit is contained in:
Georgi Gerganov 2026-06-27 17:42:42 +03:00
parent eae7149824
commit 3deb4d1711
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server-context.cpp
View File

@ -1521,7 +1521,7 @@ private:
if (params_base.use_jinja && common_chat_templates_support_preserve_thinking(chat_templates.get())) {
auto it = params_base.default_template_kwargs.find("preserve_thinking");
if (it == params_base.default_template_kwargs.end()) {
SRV_WRN("%s\n", "chat template supports 'preserve_thinking' - consider using --chat-template-kwargs \"{\\\"preserve_thinking\\\": true}\"");
SRV_WRN("%s\n", "chat template supports 'preserve_thinking' - consider using --chat-template-kwargs \"{\\\"preserve_thinking\\\": true}\" (ref: https://docs.z.ai/guides/capabilities/thinking-mode#preserved-thinking)");
}
}