--enable-reasoning is deprecated

#4
by SuperbEmphasis - opened

According the the vllm changelog (since may), this flag is deprecated or no longer in use.
https://github.com/vllm-project/vllm/pull/17452

It stills shows as deprecated, but I also just realized one cannot disable disable thinking on this model.

Qwen org

Hi, --enable-reasoning actually means enabling the reasoning parser, such that the API response contains the reasoning_content field. Otherwise, the thinking content is in the content field. this option doen't control the thinking behavior of the model.

The option was kept in the example command to maintain compatiblity with the older versions of vLLM and as of 0.9.2 this option has not been removed.

Sign up or log in to comment