[Usage]: What version of vllm is required for deepseek v3.1

[F0undLinks]

Your current environment

The output of `python collect_env.py`

What version of vllm is required for deepseek v3.1

How would you like to use vllm

I want to run inference of a [specific model](put link here). I don't know how to integrate it with vllm.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[jeejeelee]

All recent versions support this model

[F0undLinks]

All recent versions support this model

Is vllm0.8.5 ok？

[jeejeelee]

It might be a bit old, you can try it, if it doesn't work, try the latest release version

[WyInnovate]

It might be a bit old, you can try it, if it doesn't work, try the latest release version

v0.10.1.1 vLLM deployed with DeepSeek v3.1 support both thinking and non-thinking or tool-call?

[cjackal]

It might be a bit old, you can try it, if it doesn't work, try the latest release version

v0.10.1.1 vLLM deployed with DeepSeek v3.1 support both thinking and non-thinking or tool-call?

There is a few ongoing bugfix PRs like #23437, #23618 but yes it supports.

[WyInnovate]

It might be a bit old, you can try it, if it doesn't work, try the latest release version

v0.10.1.1 vLLM deployed with DeepSeek v3.1 support both thinking and non-thinking or tool-call?

There is a few ongoing bugfix PRs like #23437, #23618 but yes it supports.

Thank you for your reply. Looking forward to merging and releasing a new version as soon as possible