Instructions to use intel-ai/MiniMax-M2.7-NVFP4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use intel-ai/MiniMax-M2.7-NVFP4-AutoRound with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="intel-ai/MiniMax-M2.7-NVFP4-AutoRound", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("intel-ai/MiniMax-M2.7-NVFP4-AutoRound", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("intel-ai/MiniMax-M2.7-NVFP4-AutoRound", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use intel-ai/MiniMax-M2.7-NVFP4-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "intel-ai/MiniMax-M2.7-NVFP4-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intel-ai/MiniMax-M2.7-NVFP4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/intel-ai/MiniMax-M2.7-NVFP4-AutoRound

SGLang

How to use intel-ai/MiniMax-M2.7-NVFP4-AutoRound with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "intel-ai/MiniMax-M2.7-NVFP4-AutoRound" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intel-ai/MiniMax-M2.7-NVFP4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "intel-ai/MiniMax-M2.7-NVFP4-AutoRound" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intel-ai/MiniMax-M2.7-NVFP4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use intel-ai/MiniMax-M2.7-NVFP4-AutoRound with Docker Model Runner:
```
docker model run hf.co/intel-ai/MiniMax-M2.7-NVFP4-AutoRound
```

INC4AI commited on about 8 hours ago

Commit

0826b00

verified ·

1 Parent(s): 2e4b629

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -43,16 +43,18 @@ The checkpoint requires an inference implementation supporting AutoRound's nvfp4
 The evaluated setup used vLLM 0.32.0 with the QDQ plugin from Intel Neural Compressor PR #2621 (https://github.com/intel/neural-compressor/pull/2621). Install the plugin in the same Python environment as vLLM:
 git clone https://github.com/intel/neural-compressor.git
 cd neural-compressor
 python -m pip install --no-build-isolation -e benchmark/vllm-qdq-plugin/
 This inference path uses FP4 Marlin kernels with activation quantize-dequantize (QDQ), rather than native NVFP4 hardware computation.
 ### vLLM Usage
 Replace the model path with your local checkpoint directory:
 NCCL_NVLS_ENABLE=0 \
 VLLM_QDQ=1 \
 vllm serve /path/to/MiniMax-M2.7-NVFP4-E5M3-AutoRound \
@@ -67,7 +69,7 @@ vllm serve /path/to/MiniMax-M2.7-NVFP4-E5M3-AutoRound \
   --kv-cache-dtype fp8 \
   --gpu-memory-utilization 0.85 \
   --port 8001
 Adjust context length and GPU memory utilization according to available hardware. FP8 KV cache is a runtime setting, separate from the checkpoint's weight and activation quantization.
 ## Evaluation
@@ -85,11 +87,13 @@ Recovery is the quantized score divided by the supplied original-model baseline.
 ## Generate the Model
 auto_round MiniMaxAI/MiniMax-M2.7 \
   --model_free \
   --scheme NVFP4_E5M3 \
   --format auto_round \
   --output_dir ./MiniMax-M2.7-NVFP4-E5M3-AutoRound
 ## Ethical Considerations and Limitations

 The evaluated setup used vLLM 0.32.0 with the QDQ plugin from Intel Neural Compressor PR #2621 (https://github.com/intel/neural-compressor/pull/2621). Install the plugin in the same Python environment as vLLM:
+```bash
 git clone https://github.com/intel/neural-compressor.git
 cd neural-compressor
 python -m pip install --no-build-isolation -e benchmark/vllm-qdq-plugin/
+```
 This inference path uses FP4 Marlin kernels with activation quantize-dequantize (QDQ), rather than native NVFP4 hardware computation.
 ### vLLM Usage
 Replace the model path with your local checkpoint directory:
+```bash
 NCCL_NVLS_ENABLE=0 \
 VLLM_QDQ=1 \
 vllm serve /path/to/MiniMax-M2.7-NVFP4-E5M3-AutoRound \
   --kv-cache-dtype fp8 \
   --gpu-memory-utilization 0.85 \
   --port 8001
+```
 Adjust context length and GPU memory utilization according to available hardware. FP8 KV cache is a runtime setting, separate from the checkpoint's weight and activation quantization.
 ## Evaluation
 ## Generate the Model
+```bash
 auto_round MiniMaxAI/MiniMax-M2.7 \
   --model_free \
   --scheme NVFP4_E5M3 \
   --format auto_round \
   --output_dir ./MiniMax-M2.7-NVFP4-E5M3-AutoRound
+```
 ## Ethical Considerations and Limitations