Hy-Embodied-VLM-1.0

# Install uv once (skip if you already have it)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Create a fresh venv (Python 3.10+)
uv venv --python 3.12
source .venv/bin/activate

# Clone the repo (provides the vLLM plugin and example scripts)
git clone https://github.com/Tencent-Hunyuan/HY-Embodied
cd HY-Embodied

# One-shot install: vllm + torch + torchvision + transformers at matching
# versions, with the CUDA build picked from your driver.
uv pip install vllm==0.14.1 --torch-backend auto

# Install this repo's vLLM plugin (registers HYV3VL model + parsers)
uv pip install -e Hy-Embodied-VLM-1.0/inference/vllm/

# TP=4 by default; override MODEL_PATH / TP / PORT via env vars.
bash Hy-Embodied-VLM-1.0/inference/vllm/serve.sh

curl http://127.0.0.1:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy_a3b",
    "messages": [{"role": "user", "content": "Describe how to grasp a cup."}],
    "max_tokens": 512,
    "chat_template_kwargs": {"enable_thinking": true}
  }'

import base64
from pathlib import Path
from openai import OpenAI  # pip install "openai>=1.30" pillow

client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="EMPTY")

# --- text-only ---
resp = client.chat.completions.create(
    model="hy_a3b",
    messages=[{"role": "user", "content": "How do you open a fridge?"}],
    max_tokens=512,
    temperature=0.7,
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
msg = resp.choices[0].message
if getattr(msg, "reasoning_content", None):
    print("[thinking]", msg.reasoning_content)
print("[answer]  ", msg.content)

# --- image + text ---
def encode_image(path):
    mime = "image/jpeg" if path.lower().endswith((".jpg", ".jpeg")) else "image/png"
    return f"data:{mime};base64,{base64.b64encode(Path(path).read_bytes()).decode()}"

resp = client.chat.completions.create(
    model="hy_a3b",
    messages=[{
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": encode_image("example.jpg")}},
            {"type": "text", "text": "Describe the image in detail."},
        ],
    }],
    max_tokens=1024,
    temperature=0.7,
    extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)
print(resp.choices[0].message.content)

uv pip install torch==2.9.1 torchvision==0.24.1 --torch-backend auto
uv pip install transformers==4.57.6 accelerate pillow

# Run the demo (single image + a small batch; thinking and non-thinking modes)
cd Hy-Embodied-VLM-1.0/inference/transformers
python infer_hf.py

@article{tencent2026hyembodiedvlm10,
  title         = {Hy-Embodied-VLM-1.0: Efficient Physical-World Agents},
  author        = {Wang, Ziyi and Yu, Xumin and Rao, Yongming and Ling, Yonggen and Li, Yunheng and Wang, Oran and Gao, Mingqi and Zhou, Yuchen and Liang, Yves and Liu, Zuyan and others},
  year          = {2026},
  eprint        = {2607.12894},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2607.12894}
}

@article{tencent2026hyembodied05,
  title         = {HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents},
  author        = {Team, HY and Yu, Xumin and Liu, Zuyan and Wang, Ziyi and Zhang, He and Rao, Yongming and Liu, Fangfu and Zhang, Yani and Zhao, Ruowen and Wang, Oran and others},
  year          = {2026},
  eprint        = {2604.07430},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2604.07430}
}