pip install -U "huggingface_hub[hf_xet]"
 
# Log in once; the token is cached at ~/.cache/huggingface/token
hf auth login
 
# Sanity check: should print your username and orgs
hf auth whoami

docker pull vllm/vllm-openai:v0.20.0

# vllm serve nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 \
# vllm serve nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 \
vllm serve nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 \
  --host 0.0.0.0 \
  --max-model-len 131072 \
  --tensor-parallel-size 1 \
  --trust-remote-code \
  --video-pruning-rate 0.5 \
  --max-num-seqs 384 \
  --allowed-local-media-path / \
  --media-io-kwargs '{"video": {"fps": 2, "num_frames": 256}}' \
  --reasoning-parser nemotron_v3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --kv-cache-dtype fp8 # Omit this for BF16

docker pull vllm/vllm-openai:v0.20.0

WEIGHTS=/path/to/nemotron-3-nano-omni-weights

# The image does not include audio packages so we need to install them with "pip install vllm[audio]" as done in the command below
docker run --rm -it \
  --gpus all \
  --ipc=host -p 8000:8000 \
  --shm-size=16g \
  --name vllm-nemotron-omni \
  -v "${WEIGHTS}:/model:ro" \
  --entrypoint /bin/bash \
  vllm/vllm-openai:v0.20.0 -c  \
  "pip install vllm[audio] && vllm serve /model \
  --served-model-name=nemotron_3_nano_omni \
  --max-num-seqs 8 \
  --max-model-len 131072 \
  --port 8000 \
  --trust-remote-code \
  --gpu-memory-utilization 0.8 \
  --limit-mm-per-prompt '{\"video\": 1, \"image\": 1, \"audio\": 1}' \
  --media-io-kwargs '{\"video\": {\"fps\": 2,  \"num_frames\": 256}}' \
  --allowed-local-media-path=/ \
  --enable-prefix-caching \
  --max-num-batched-tokens 32768 \
  --reasoning-parser nemotron_v3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder"

curl -sS http://localhost:8000/v1/models | python3 -m json.tool

  --gpu-memory-utilization=0.70 \
  --max-model-len=32768 \

docker pull lmsysorg/sglang:dev-cu13-nemotronh-nano-omni-reasoning-v3

WEIGHTS=/path/to/nemotron-3-nano-omni-weights

# The image does not include audio packages so we need to install them with "pip install librosa" as done in the command below
docker run --gpus all -it --rm \
  -p 30000:30000 \
  -v "${WEIGHTS}:/model:ro" \
  --shm-size 16g \
  lmsysorg/sglang:dev-cu13-nemotronh-nano-omni-reasoning-v3 \
  bash -c "pip install librosa && python3 -m sglang.launch_server --model-path /model \
  --host 0.0.0.0 \
  --port 30000 \
  --trust-remote-code \
  --mem-fraction-static 0.8 \
  --max-running-requests 8 \
  --tool-call-parser qwen3_coder \
  --reasoning-parser nemotron_3"

curl -sS http://localhost:30000/v1/models | python3 -m json.tool

  --mem-fraction-static=0.70 \
  --context-length=32768 \

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="")
MODEL = "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4"

import base64
 
def image_to_data_url(path: str) -> str:
    with open(path, "rb") as f:
        b64 = base64.b64encode(f.read()).decode("utf-8")
    return f"data:image/jpeg;base64,{b64}"
 
image_url = image_to_data_url("media/example1a.jpeg")
 
response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image in detail."},
                {"type": "image_url", "image_url": {"url": image_url}},
            ],
        }
    ],
    max_tokens=1024,
    temperature=0.2,
    extra_body={"top_k": 1, "chat_template_kwargs": {"enable_thinking": False}},
)
print(response.choices[0].message.content)

from pathlib import Path
 
audio_url = Path("media/2414-165385-0000.wav").resolve().as_uri()
 
response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "audio_url", "audio_url": {"url": audio_url}},
                {"type": "text", "text": "Transcribe this audio."},
            ],
        }
    ],
    max_tokens=1024,
    temperature=0.2,
    extra_body={"top_k": 1, "chat_template_kwargs": {"enable_thinking": False}},
)
print(response.choices[0].message.content)

from pathlib import Path
 
video_url = Path("media/demo.mp4").resolve().as_uri()
reasoning_budget = 16384
grace_period = 1024
 
response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "video_url", "video_url": {"url": video_url}},
                {"type": "text", "text": "Describe this video."},
            ],
        }
    ],
    max_tokens=20480,
    temperature=0.6,
    top_p=0.95,
    extra_body={
        "thinking_token_budget": reasoning_budget + grace_period,
        "chat_template_kwargs": {
            "enable_thinking": True,
            "reasoning_budget": reasoning_budget,
        },
        "mm_processor_kwargs": {"use_audio_in_video": False},
    },
)
print(response.choices[0].message.content)

curl -sS http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4","messages":[{"role":"user","content":"Hello, what can you do?"}],"temperature":0.2,"top_k":1}' \
  | python3 -c "import sys,json; print(json.load(sys.stdin)['choices'][0]['message']['content'])"

#!/usr/bin/env python3
"""Send PDF page(s) as images to a vLLM /v1/chat/completions endpoint."""
from __future__ import annotations
 
import argparse, base64, sys
from io import BytesIO
from pathlib import Path
 
import requests
 
try:
    import fitz
    from PIL import Image
except ImportError:
    print("Install: pip install pymupdf pillow requests", file=sys.stderr)
    sys.exit(1)
 
USER_PROMPT = (
    "Summarize this PDF page: main topic, section headings, important facts "
    "or bullets, and a brief note on each figure or table. "
    "Do not invent text you cannot read."
)
API_URL = "http://localhost:8000/v1/chat/completions"
MODEL = "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4"
MAX_TOKENS = 32000
DPI = 150
 
 
def page_to_b64(pdf_path: str, idx: int) -> str:
    doc = fitz.open(pdf_path)
    z = DPI / 72.0
    pix = doc.load_page(idx).get_pixmap(matrix=fitz.Matrix(z, z))
    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
    doc.close()
    buf = BytesIO()
    img.save(buf, format="PNG")
    return base64.b64encode(buf.getvalue()).decode("ascii")
 
 
def chat(url, model, b64, text, max_tokens):
    r = requests.post(url, json={
        "model": model,
        "messages": [{"role": "user", "content": [
            {"type": "text", "text": text},
            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}},
        ]}],
        "max_tokens": max_tokens,
        "stream": False,
        "temperature": 0.2,
        "chat_template_kwargs": {"enable_thinking": False},
    }, timeout=120)
    r.raise_for_status()
    return r.json()["choices"][0]["message"]["content"]
 
 
def main():
    p = argparse.ArgumentParser()
    p.add_argument("pdf")
    p.add_argument("--page", type=int, default=0)
    p.add_argument("--all-pages", action="store_true")
    p.add_argument("-o", "--output")
    p.add_argument("--url", default=API_URL)
    p.add_argument("--model", default=MODEL)
    p.add_argument("--max-tokens", type=int, default=MAX_TOKENS)
    a = p.parse_args()
 
    doc = fitz.open(a.pdf); n = len(doc); doc.close()
    pages = range(n) if a.all_pages else [a.page]
    parts = [f"# Extracted: {Path(a.pdf).name}\n\n*Pages: {n}*\n"] if a.all_pages else []
 
    for i in pages:
        print(f"Page {i+1}/{n} ...", file=sys.stderr)
        b64 = page_to_b64(a.pdf, i)
        text = chat(a.url, a.model, b64, f"Page {i+1}.\n\n{USER_PROMPT}", a.max_tokens)
        parts.append(f"\n---\n\n## Page {i+1}\n\n{text.strip()}\n" if a.all_pages else text.strip())
 
    out = "\n".join(parts)
    if a.output:
        Path(a.output).write_text(out + "\n", encoding="utf-8")
    else:
        print(out)
 
if __name__ == "__main__":
    main()

python3 pdf_vlm_chat.py /path/to/your_document.pdf --page 0

python3 pdf_vlm_chat.py /path/to/your_document.pdf --all-pages -o extracted.md

"chat_template_kwargs": {"enable_thinking": false}

from typing import Any, Dict, List

from openai import OpenAI
from transformers import AutoTokenizer


class ThinkingBudgetClient:
    def __init__(self, base_url: str, api_key: str, tokenizer_name_or_path: str):
        self.tokenizer = AutoTokenizer.from_pretrained(
            tokenizer_name_or_path, trust_remote_code=True
        )
        self.client = OpenAI(base_url=base_url, api_key=api_key)

    def chat_completion(
        self,
        model: str,
        messages: List[Dict[str, Any]],
        reasoning_budget: int = 512,
        max_tokens: int = 1024,
        **kwargs,
    ) -> Dict[str, Any]:
        assert max_tokens > reasoning_budget, (
            f"reasoning_budget must be less than max_tokens. "
            f"Got {max_tokens=} and {reasoning_budget=}"
        )

        # Step 1: generate only the reasoning trace up to the requested budget.
        response = self.client.chat.completions.create(
            model=model,
            messages=messages,
            max_tokens=reasoning_budget,
            extra_body={
                "top_k": 1,
                "chat_template_kwargs": {
                    "enable_thinking": True,
                },
            },
            **kwargs,
        )
        reasoning_content = response.choices[0].message.content or ""
        if "</think>" not in reasoning_content:
            print("No </think> found in reasoning content")
            reasoning_content = f"{reasoning_content}</think>\n\n"

        reasoning_tokens_len = len(
            self.tokenizer.encode(reasoning_content, add_special_tokens=False)
        )
        remaining_tokens = max_tokens - reasoning_tokens_len
        assert remaining_tokens > 0, (
            f"No tokens remaining for response ({remaining_tokens=}). "
            "Increase max_tokens or lower reasoning_budget."
        )

        # Step 2: continue from the closed reasoning trace and ask for the final answer.
        continued_messages = messages + [
            {"role": "assistant", "content": reasoning_content}
        ]
        prompt = self.tokenizer.apply_chat_template(
            continued_messages,
            tokenize=False,
            continue_final_message=True,
        )
        response = self.client.completions.create(
            model=model,
            prompt=prompt,
            max_tokens=remaining_tokens,
            extra_body={"top_k": 1},
            **kwargs,
        )

        return {
            "reasoning_content": reasoning_content.strip(),
            "content": response.choices[0].text,
            "finish_reason": response.choices[0].finish_reason,
        }

--media-io-kwargs '{"video": {"fps": 2, "num_frames": 256}}'

@misc{nvidia2026nemotron3nanoomni,
      title={Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence},
      author={NVIDIA},
      year={2026},
      eprint={2604.24954},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2604.24954},
}