Text Generation
Transformers
Safetensors
minimax_m2
conversational
custom_code
fp8

Invalid reasoning-parser

#37
by willamazon1 - opened

I follow the deployment https://huggingface.co/MiniMaxAI/MiniMax-M2/blob/main/docs/vllm_deploy_guide.md, but encounter the following error:

vllm serve: error: argument --reasoning-parser: invalid choice: 'minimax_m2_append_think' (choose from 'deepseek_r1', 'glm45', 'openai_gptoss', 'granite', 'hunyuan_a13b', 'mistral', 'qwen3', 'seed_oss', 'step3')

MiniMax org

do you use nightly vllm?

The parser doesn't seem to be working, because I'm receiving a message from the model in the <think>reasoning</think>answer format, and it's not parsed. I thought the reasoning part would be in a separate reasoning_content field. But it's not separated from the content by the minimax_m2_append_think parser.

I got same error. and I'v installed the latest vllm.

You can use --reasoning-parser minimax_m2.

SAFETENSORS_FAST_GPU=1 CUDA_VISIBLE_DEVICES=4,5,6,7 vllm serve /data2/models/MiniMax-M2 --trust-remote-code --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser minimax_m2 --reasoning-parser minimax_m2
INFO 11-12 07:03:34 [init.py:216] Automatically detected platform cuda.
usage: vllm serve [model_tag] [options]
vllm serve: error: argument --reasoning-parser: invalid choice: 'minimax_m2' (choose from deepseek_r1, glm45, openai_gptoss, granite, hunyuan_a13b, mistral, qwen3, seed_oss, step3)

@sliontc do you use nightly vllm?

Sign up or log in to comment