Instructions to use LilaRest/gemma-4-31B-it-NVFP4-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LilaRest/gemma-4-31B-it-NVFP4-turbo with Transformers:

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

pipe = pipeline("text-generation", model="LilaRest/gemma-4-31B-it-NVFP4-turbo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("LilaRest/gemma-4-31B-it-NVFP4-turbo")
model = AutoModelForCausalLM.from_pretrained("LilaRest/gemma-4-31B-it-NVFP4-turbo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LilaRest/gemma-4-31B-it-NVFP4-turbo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LilaRest/gemma-4-31B-it-NVFP4-turbo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LilaRest/gemma-4-31B-it-NVFP4-turbo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LilaRest/gemma-4-31B-it-NVFP4-turbo

SGLang

How to use LilaRest/gemma-4-31B-it-NVFP4-turbo 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 "LilaRest/gemma-4-31B-it-NVFP4-turbo" \
    --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": "LilaRest/gemma-4-31B-it-NVFP4-turbo",
		"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 "LilaRest/gemma-4-31B-it-NVFP4-turbo" \
        --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": "LilaRest/gemma-4-31B-it-NVFP4-turbo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LilaRest/gemma-4-31B-it-NVFP4-turbo with Docker Model Runner:
```
docker model run hf.co/LilaRest/gemma-4-31B-it-NVFP4-turbo
```

Error using your recommended docker

by robinsyihab - opened Apr 11

Discussion

robinsyihab

Apr 11

Error using your recommended docker:

 File "/usr/local/lib/python3.12/dist-packages/vllm/compilation/decorators.py", line 355, in __init__
   old_init(self, **kwargs)
 File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/transformers/multimodal.py", line 277, in __init__
   super(SupportsMRoPE, self).__init__(vllm_config=vllm_config, prefix=prefix)
 File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/transformers/causal.py", line 35, in __init__
   super(VllmModelForTextGeneration, self).__init__(
 File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/transformers/base.py", line 159, in __init__
   self._patch_config()
 File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/transformers/base.py", line 218, in _patch_config
   if sub_config.dtype != (dtype := self.config.dtype):
      ^^^^^^^^^^^^^^^^
(EngineCore pid=425) ERROR 04-11 13:57:59 [core.py:1099] AttributeError: 'NoneType' object has no attribute 'dtype'

LilaRest

Owner Apr 11

Looks like a transformers version issue. Run pip install transformers>=5.5.0 inside your container and try again.

If it still doesn't work, can you share your setup? (GPU model, vLLM version, transformers version, CUDA version, and the full docker/vllm command you're running).
That'll help me reproduce it.

JohnUser

Apr 11

@robi

Error using your recommended docker:

Try this one:

  vllm:
    image: vllm/vllm-openai:cu130-nightly
    container_name: vllm
    restart: unless-stopped
    runtime: nvidia
    ipc: host
    ports:
      - "8000:8000"
    environment:
      - HF_TOKEN=${HF_TOKEN}
    volumes:
      #Your HuggingFace cache
      - /var/lib/vllm/huggingface:/root/.cache/huggingface
    entrypoint: /bin/sh
    command:
      - -c
      - |
        pip install --no-cache-dir 'transformers>=5.5.0' && \
        exec vllm serve LilaRest/gemma-4-31B-it-NVFP4-turbo \
        --quantization modelopt \
        --kv-cache-dtype fp8 \
        --gpu-memory-utilization 0.95 \
        --max-model-len auto \
        --max-num-seqs 128 \
        --max-num-batched-tokens 8192 \
        --enable-prefix-caching \
        --trust-remote-code \
        --enable-auto-tool-choice \
        --tool-call-parser gemma4

It uses a smart hack to update transformers every time the image is spun up

robinsyihab

Apr 12

The error I shared occurred after I updated Transformers as mentioned in the README, before update the error is unrecognized gemma4 type

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