本地部署指南

SAFETENSORS_FAST_GPU=1 vllm serve \
    MiniMaxAI/MiniMax-M2.7 --trust-remote-code \
    --tensor-parallel-size 4 \
    --enable-auto-tool-choice --tool-call-parser minimax_m2 \
    --reasoning-parser minimax_m2_append_think

SAFETENSORS_FAST_GPU=1 vllm serve \
    MiniMaxAI/MiniMax-M2.7 --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

python -m sglang.launch_server \
    --model-path MiniMaxAI/MiniMax-M2.7 \
    --tp-size 4 \
    --tool-call-parser minimax-m2 \
    --reasoning-parser minimax-append-think \
    --host 0.0.0.0 \
    --trust-remote-code \
    --port 8000 \
    --mem-fraction-static 0.85

python -m sglang.launch_server \
    --model-path MiniMaxAI/MiniMax-M2.7 \
    --tp-size 8 \
    --ep-size 8 \
    --tool-call-parser minimax-m2 \
    --reasoning-parser minimax-append-think \
    --host 0.0.0.0 \
    --trust-remote-code \
    --port 8000 \
    --mem-fraction-static 0.85

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "MiniMaxAI/MiniMax-M2.7",
        "messages": [
            {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant."}]},
            {"role": "user", "content": [{"type": "text", "text": "Who won the world series in 2020?"}]}
        ]
    }'

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="not-needed",
)

response = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"},
    ],
    temperature=1.0,
    top_p=0.95,
    max_tokens=8192,
)

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

mlx_lm.generate \
  --model mlx-community/MiniMax-M2.7-6bit \
  --prompt "解释神经网络中混合专家模型的概念。" \
  --max-tokens 8192 \
  --temp 1.0

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

# 根据内存选择合适的变体 — 参见上方「模型选择指南」
model, tokenizer = load("mlx-community/MiniMax-M2.7-6bit")

sampler = make_sampler(temp=1.0, top_p=0.95, top_k=40)

messages = [{"role": "user", "content": "用 Python 写一个查找素数的函数。"}]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    max_tokens=8192,
    sampler=sampler,
    verbose=True,
)
print(response)

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mlx-community/MiniMax-M2.7-6bit",
    "messages": [{"role": "user", "content": "你好！"}],
    "temperature": 1.0,
    "top_p": 0.95,
    "max_tokens": 8192
  }'

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="not-needed",
)

response = client.chat.completions.create(
    model="mlx-community/MiniMax-M2.7-6bit",
    messages=[{"role": "user", "content": "你好！"}],
    temperature=1.0,
    top_p=0.95,
    max_tokens=8192,
)

# content 已自动分离，strip() 去除前导换行
print(response.choices[0].message.content.strip())