Instructions to use nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8

SGLang

How to use nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 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 "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8" \
    --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": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8",
		"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 "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8" \
        --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": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8
```

dont run FP8, error

by chuanyizjc - opened May 9, 2025

Discussion

chuanyizjc

May 9, 2025

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/dist-packages/transformers/utils/hub.py", line 491, in cached_files
raise OSError(
OSError: We couldn't connect to 'https://huggingface.co' to load the files, and couldn't find them in the cached files.
Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.

abatpool

Jul 25, 2025

•

edited Jul 25, 2025

Did you find a solution to it @chuanyizjc . Even if I am having the model placed at local path and I am finding the same error as above. I have tried to add print statement at each step to find out that , it able access insides of model file, still while launching/serving the above error is incurred

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