部署 MiniMax-M2.7

docker run --gpus all \
  --shm-size 32g \
  -p 30000:30000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  --ipc=host \
  lmsysorg/sglang:v0.5.10.post1 \
  sglang serve \
  --model-path MiniMaxAI/MiniMax-M2.7 \
  --tp 4 \
  --tool-call-parser minimax-m2 \
  --reasoning-parser minimax-append-think \
  --trust-remote-code \
  --mem-fraction-static 0.85 \
  --host 0.0.0.0 \
  --port 30000

--env "HF_TOKEN=<your-hf-token>"

curl http://localhost:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMaxAI/MiniMax-M2.7",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "用 Python 写一个判断素数的函数。"}
    ],
    "max_tokens": 2048
  }'

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

response = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[{"role": "user", "content": "解释混合专家模型。"}],
    max_tokens=2048,
)

print(response.choices[0].message.content)