Text Generation
Transformers
Safetensors
minimax_m2
conversational
custom_code
fp8

Docs change

#2
by zhaochenyang20 - opened

Since it has not been released yet, you need to manually build it from the source code

delete this.

python -m sglang.launch_server
--model-path MiniMaxAI/MiniMax-M2
--tp-size 8
--ep-size 8
--tool-call-parser minimax-m2
--trust-remote-code
--reasoning-parser minimax-m2
--mem-fraction-static 0.85

Recommended command on H200.

After startup, you can test the vLLM OpenAI-compatible API with the following command:

After fireup, you can test SGLang OpenAI-compatible API with the following command:

curl http://localhost:30000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "MiniMaxAI/MiniMax-M2",
        "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?"}]}
        ]
    }'
MiniMax org

After startup, you can test the vLLM OpenAI-compatible API with the following command:

After fireup, you can test SGLang OpenAI-compatible API with the following command:

curl http://localhost:30000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "MiniMaxAI/MiniMax-M2",
        "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?"}]}
        ]
    }'

This has been fixed. Have you pulled the latest version?

sriting changed discussion status to closed

Sign up or log in to comment