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
```

shmuli commited on Nov 13, 2025

Commit

441184b

verified ·

1 Parent(s): 420ba7d

Trying to fix issues with extra arguments to the model

Browse files

Files changed (1) hide show

modeling_decilm.py +1 -0

modeling_decilm.py CHANGED Viewed

@@ -503,6 +503,7 @@ class DeciLMFlashAttention2(DeciLMAttention):
             use_cache: bool = False,
             cache_position: Optional[torch.LongTensor] = None,
             position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,  # will become mandatory in v4.45
     ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
         output_attentions = False

             use_cache: bool = False,
             cache_position: Optional[torch.LongTensor] = None,
             position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,  # will become mandatory in v4.45
+            **kwargs,
     ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
         output_attentions = False