Instructions to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", 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_3-Nemotron-Super-49B-v1_5", trust_remote_code=True, dtype="auto")

Inference
Local Apps Settings

vLLM

How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5"
# 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_3-Nemotron-Super-49B-v1_5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5

SGLang

How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 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_3-Nemotron-Super-49B-v1_5" \
    --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_3-Nemotron-Super-49B-v1_5",
		"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_3-Nemotron-Super-49B-v1_5" \
        --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_3-Nemotron-Super-49B-v1_5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
```

Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced `NEED_SETUP_CACHE_CLASSES_MAPPING`

by blewis-hir - opened Nov 9, 2025

base: refs/heads/main

←

from: refs/pr/9

Discussion Files changed

+14

-2

blewis-hir

Nov 9, 2025

•

edited Nov 9, 2025

This should fix using the model with new transformers versions

Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced the existing dictionaryf4a9fe8f

blewis-hir changed pull request title from Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced the existing dictionary to Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced `NEED_SETUP_CACHE_CLASSES_MAPPING` Nov 9, 2025

blewis-hir

Nov 9, 2025

See these transformers commits:
https://github.com/huggingface/transformers/commit/a2e76b908b1fd68a71117be1bcc9389869c6f445
https://github.com/huggingface/transformers/commit/242bb2cafccec9f90479f5f688bca9d240b1031f

Make changes backwards compatible with old `transformers` versions2b886402

Fix incorrect version check277a89dd

Fix crash on model forward with fix by @shmuli57d602ba

NePe

Nov 24, 2025

•

edited Nov 24, 2025

Hmm is this really enough? I had to change a few lines in variable_cache.py too for the latest transformers. https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5/discussions/12

blewis-hir

Nov 25, 2025

@NePe It worked for me... but I will check and see if I missed something that you fixed

NePe

Nov 29, 2025

I checked your code and it has a few syntax errors/typos and ALL_STATIC_CACHE_IMPLEMENTATIONS is a tuple of str so there is no way this could work:
https://github.com/huggingface/transformers/blob/v4.57.3/src/transformers/generation/configuration_utils.py#L46

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment