How to make thinking stop, so you can use none, low, mid, high thinking
Enabling no-think / enable_thinking=false on Step-3.7-Flash (vLLM)
Step-3.7's stock chat template always opens a block, so the model reasons on every turn. Two small edits make it
honor the standard enable_thinking switch (and reasoning_effort), defaulting to thinking ON.
- Chat template (chat_template.jinja in your model dir)
Add a flag at the top:
{%- set thinking_enabled = not (enable_thinking is defined and enable_thinking is false) %}
At the generation prompt, emit an empty closed block when disabled (mirrors Qwen3):
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if thinking_enabled %}{{- '<think>\n' }}
{%- else %}{{- '<think>\n\n</think>\n\n' }}{%- endif %}
{%- endif %}
Gate the prior-turn re-emission and the Reasoning: effort hint on thinking_enabled too.
- Reasoning parser (vllm/reasoning/step3p5_reasoning_parser.py)
In __init__, read the per-request flag:
chat_kwargs = kwargs.get("chat_template_kwargs", {}) or {}
self.thinking_enabled = chat_kwargs.get("enable_thinking", True)
In extract_reasoning, short-circuit when disabled and no </think> appears:
if self.end_token not in model_output and not self.thinking_enabled:
return None, model_output or None
Streaming needs no change — the empty closed block puts in the prompt, so the serving layer marks reasoning
ended and routes deltas to content automatically.
Use it (either works):
"chat_template_kwargs": {"enable_thinking": false} // explicit off
"reasoning_effort": "none" // also sets enable_thinking=false
"reasoning_effort": "high" // thinking on + effort hint
Unset = thinking on (unchanged default).
Use it (either works):
"chat_template_kwargs": {"enable_thinking": false} // explicit off
"reasoning_effort": "none" // also sets enable_thinking=false
"reasoning_effort": "high" // thinking on + effort hint
Unset = thinking on (unchanged default).