dots3-note-prev

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")

response = client.chat.completions.create(
    model="dots3-note-prev",
    messages=[
        {"role": "user", "content": "Hello! Can you briefly introduce yourself?"},
    ],
    temperature=1.0,
    top_p=0.95,
    max_tokens=256,
    # Set enable_thinking=True for reasoning; False returns a direct response.
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(response.choices[0].message.content)

examples = {
    "image": [
        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png"}},
        {"type": "text", "text": "How many cats are in this image?"},
    ],
    "audio": [
        {"type": "audio_url", "audio_url": {"url": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3"}},
        {"type": "text", "text": "Transcribe this nursery rhyme."},
    ],
    "video": [
        {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
        {"type": "text", "text": "Describe the performance and what can be heard."},
    ],
}
messages = [{"role": "user", "content": examples["image"]}]

pip install accelerate pillow torchcodec kernels==0.16.0 "transformers @ git+https://github.com/huggingface/transformers.git@refs/pull/47844/head"

from transformers import AutoModelForMultimodalLM, AutoProcessor

model_id = "dots-studio/dots3-note-prev-fp8"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, dtype="auto", device_map="auto")

messages = [
    {"role": "user", "content": "Hello! Please briefly introduce yourself."},
]
inputs = processor.tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
    enable_thinking=False,
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(processor.decode(outputs[0, inputs.input_ids.shape[1] :], skip_special_tokens=True))

docker run --gpus all --ipc=host -p 8000:8000 \
  lmsysorg/sglang:dev-dots3-note \
  sglang serve \
    --model-path dots-studio/dots3-note-prev-fp8 \
    --served-model-name dots3-note-prev \
    --host 0.0.0.0 \
    --port 8000 \
    --context-length 524288 \
    --enable-dp-attention \
    --dp-size 8 \
    --tp-size 8 \
    --ep-size 8 \
    --moe-dense-tp-size 1 \
    --page-size 64 \
    --trust-remote-code \
    --attention-backend fa3 \
    --moe-a2a-backend deepep \
    --enable-multimodal \
    --speculative-algorithm NEXTN \
    --speculative-num-steps 3 \
    --speculative-eagle-topk 1 \
    --speculative-num-draft-tokens 4 \
    --speculative-draft-model-path dots-studio/dots3-note-prev-fp8

# Load only the language model
--language-only

# Enable OpenAI-compatible tool calling
--tool-call-parser dots

vllm serve dots-studio/dots3-note-prev-fp8 \
  --served-model-name dots3-note-prev \
  --host 0.0.0.0 \
  --tensor-parallel-size 8 \
  --enable-expert-parallel \
  --moe-backend deep_gemm \
  --max-model-len 262144

# Load only the language model
--language-model-only

# Enable three-token MTP speculative decoding
--speculative-config '{"method":"mtp","num_speculative_tokens":3}'

# Enable OpenAI-compatible automatic tool calling
--enable-auto-tool-choice --tool-call-parser dots