mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-01 00:10:21 -05:00
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