vllm serve /workspace/model \
--trust-remote-code \
--enable_expert_parallel \
--tensor-parallel-size 8 \
--enable-auto-tool-choice \
--tool-call-parser minimax_m2 \
--reasoning-parser minimax_m2_append_think \
--served-model-name MiniMax-M2
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')