Instructions to use Motif-Technologies/Motif-3-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Motif-Technologies/Motif-3-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="Motif-Technologies/Motif-3-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Motif-Technologies/Motif-3-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Motif-Technologies/Motif-3-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Motif-Technologies/Motif-3-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Motif-Technologies/Motif-3-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Motif-Technologies/Motif-3-NVFP4

SGLang

How to use Motif-Technologies/Motif-3-NVFP4 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 "Motif-Technologies/Motif-3-NVFP4" \
    --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": "Motif-Technologies/Motif-3-NVFP4",
		"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 "Motif-Technologies/Motif-3-NVFP4" \
        --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": "Motif-Technologies/Motif-3-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Motif-Technologies/Motif-3-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Motif-Technologies/Motif-3-NVFP4
```

Need arm64 build of vllm docker image for DGX Spark usage

by WiSFoR - opened 1 day ago

Discussion

WiSFoR

1 day ago

Can we have either arm64 build of vllm docker image or the vllm branch to build it manually?

TaehyunKimMotif

Motif Technologies org 1 day ago

@WiSFoR
Thank you for your interest in this! We’re planning to make the vLLM branch available soon, which will allow you to build the ARM64 Docker image manually. We really appreciate your interest and patience.

TaehyunKimMotif

Motif Technologies org 1 day ago

@WiSFoR
We’ve now made the vLLM branch available.
You can find it here: https://github.com/MotifTechnologies/vllm
Thank you again for your interest and patience!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment