Instructions to use meta-llama/Llama-4-Scout-17B-16E-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-4-Scout-17B-16E-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="meta-llama/Llama-4-Scout-17B-16E-Instruct")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("meta-llama/Llama-4-Scout-17B-16E-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("meta-llama/Llama-4-Scout-17B-16E-Instruct")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-4-Scout-17B-16E-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-4-Scout-17B-16E-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-4-Scout-17B-16E-Instruct

SGLang

How to use meta-llama/Llama-4-Scout-17B-16E-Instruct 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 "meta-llama/Llama-4-Scout-17B-16E-Instruct" \
    --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": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "meta-llama/Llama-4-Scout-17B-16E-Instruct" \
        --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": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-4-Scout-17B-16E-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
```

Any luck doing inference in 8xA100?

#57

by taytun - opened Apr 9, 2025

Discussion

taytun

Apr 9, 2025

•

edited Apr 9, 2025

Did anybody able to run inferece in 8 X A100 (80GB GPUs)?
It was such a pain to be able to load it but unable to do infer

ENV:

cupy-cuda12x==13.4.1
nvidia-cuda-cupti-cu12==12.4.127
nvidia-cuda-nvrtc-cu12==12.4.127
nvidia-cuda-runtime-cu12==12.4.127
torch==2.6.0
torchaudio==2.6.0
torchelastic==0.2.2
torchvision==0.21.0
transformers==4.51.1
vllm==0.8.3

GPUs

CODE:

from transformers import AutoProcessor, AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig,Llama4ForConditionalGeneration
import torch

# Load the model and tokenizer
model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct" 
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = Llama4ForConditionalGeneration.from_pretrained(
    model_id,
    attn_implementation="flex_attention",
    #quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)

processor = AutoProcessor.from_pretrained(model_id)

messages = [{"role": "user","content": [{"type": "text", "text": "explain me the cuda"}]}]
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=256,)
response = processor.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])[0]
print(response)
print(outputs[0])

Error message:

TorchRuntimeError: Failed running call_function <built-in function add>(*(FakeTensor(..., device='cuda:1', size=(), dtype=torch.int32), FakeTensor(..., device='cuda:0', size=(), dtype=torch.int64)), **{}):
Unhandled FakeTensor Device Propagation for aten.add.Tensor, found two different devices cuda:1, cuda:0