Instructions to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4"
# 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/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 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/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4" \
    --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/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
		"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/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4" \
        --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/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
```

Update SGLang serving commands

by b8zhong - opened Jun 16

base: refs/heads/main

←

from: refs/pr/9

Discussion Files changed

-15

Files changed (1) hide show

README.md +9 -15

README.md CHANGED Viewed

@@ -345,9 +345,9 @@ vllm serve $MODEL_CKPT \
 ### **SGLang**
-**Container (tested on 4× B200):** `docker pull lmsysorg/sglang:v0.5.12.post1`
-For more detailed information, please see this cookbook.
 **4× B200 single-node deployment (NVFP4):**
@@ -362,9 +362,7 @@ docker run -d --name nemotron-ultra-sglang \
   --ulimit stack=67108864 \
   -v $MODEL_CKPT:/model:ro \
   -e SAFETENSORS_FAST_GPU=1 \
-  -e NVIDIA_TF32_OVERRIDE=1 \
-  -e SGLANG_DISABLE_DEEP_GEMM=1 \
-  lmsysorg/sglang:v0.5.12.post1 \
   python3 -m sglang.launch_server \
   --model-path /model \
   --host 0.0.0.0 \
@@ -374,20 +372,16 @@ docker run -d --name nemotron-ultra-sglang \
   --ep-size 4 \
   --context-length 262144 \
   --mem-fraction-static 0.85 \
-  --chunked-prefill-size 32768 \
-  --fp8-gemm-backend triton \
-  --moe-runner-backend triton \
-  --mamba-scheduler-strategy no_buffer \
-  --disable-piecewise-cuda-graph \
   --reasoning-parser nemotron_3 \
   --tool-call-parser qwen3_coder \
   --speculative-algorithm EAGLE \
-  --speculative-num-steps 5 \
   --speculative-eagle-topk 1 \
-  --speculative-num-draft-tokens 5 \
-  --kv-cache-dtype fp8 \
-  --trust-remote-code \
-  --log-level info
 ```
 * **Context length:** Defaults to 256k above. To use up to 1M, set `SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1` and `--context-length 1048576`.

 ### **SGLang**
+**Container (tested on 4× B200):** `docker pull lmsysorg/sglang:v0.5.13`
+For more detailed information, please see the official [SGLang cookbook](https://docs.sglang.io/cookbook/autoregressive/NVIDIA/Nemotron3-Ultra).
 **4× B200 single-node deployment (NVFP4):**
   --ulimit stack=67108864 \
   -v $MODEL_CKPT:/model:ro \
   -e SAFETENSORS_FAST_GPU=1 \
+  lmsysorg/sglang:v0.5.13 \
   python3 -m sglang.launch_server \
   --model-path /model \
   --host 0.0.0.0 \
   --ep-size 4 \
   --context-length 262144 \
   --mem-fraction-static 0.85 \
+  --mamba-scheduler-strategy extra_buffer \
+  --mamba-backend flashinfer \
+  --attention-backend trtllm_mha \
   --reasoning-parser nemotron_3 \
   --tool-call-parser qwen3_coder \
   --speculative-algorithm EAGLE \
+  --speculative-num-steps 3 \
   --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --trust-remote-code
 ```
 * **Context length:** Defaults to 256k above. To use up to 1M, set `SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1` and `--context-length 1048576`.