Note

本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
English · 原始项目 · 上游 README
原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。

---

Unlimited OCR Works

迎接 One-shot 长视野解析（Long-horizon Parsing）时代。

Release

• [2026/07/03] 🤝 感谢百度智能云团队的支持。我们的模型现已在 百度智能云.
• [2026/06/28] 🤝 感谢 vLLM 社区 和 Tianyu Guo 的支持，我们的模型现已支持 vLLM 推理。
• [2026/06/24] 🤝 感谢 AK 为我们制作了演示。现已上线 Hugging Face Spaces.
• [2026/06/23] 📄 我们的论文现已在 arXiv. 发布
• [2026/06/23] 🤝 感谢 ModelScope 社区 的支持。我们的模型现已在 ModelScope. 上线
• [2026/06/22] 🚀 我们推出 Unlimited-OCR,，旨在将 Deepseek-OCR 再推进一步。

推理

Transformers

在 NVIDIA GPU 上使用 Hugging Face Transformers 进行推理。已在 python 3.12.3 + CUDA12.9 环境下测试通过：

torch==2.10.0
torchvision==0.25.0
transformers==4.57.1
Pillow==12.1.1
matplotlib==3.10.8
einops==0.8.2
addict==2.4.0
easydict==1.13
pymupdf==1.27.2.2
psutil==7.2.2

import os
import torch
from transformers import AutoModel, AutoTokenizer

model_name = 'baidu/Unlimited-OCR'

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(
    model_name,
    trust_remote_code=True,
    use_safetensors=True,
    torch_dtype=torch.bfloat16,
)
model = model.eval().cuda()

# ── Single image supports two configs: gundam or base ──
# gundam: base_size=1024, image_size=640, crop_mode=True
# base: base_size=1024, image_size=1024, crop_mode=False
model.infer(
    tokenizer,
    prompt='<image>document parsing.',
    image_file='your_image.jpg',
    output_path='your/output/dir',
    base_size=1024, image_size=640, crop_mode=True,
    max_length=32768,
    no_repeat_ngram_size=35, ngram_window=128,
    save_results=True,
)

# ── Multi page / PDF only uses base (image_size=1024) ──
model.infer_multi(
    tokenizer,
    prompt='<image>Multi page parsing.',
    image_files=['page1.png', 'page2.png', 'page3.png'],
    output_path='your/output/dir',
    image_size=1024,
    max_length=32768,
    no_repeat_ngram_size=35, ngram_window=1024,
    save_results=True,
)

# ── PDF (convert pages to images, then multi-page parsing) ──
import tempfile, fitz  # PyMuPDF

def pdf_to_images(pdf_path, dpi=300):
    doc = fitz.open(pdf_path)
    tmp_dir = tempfile.mkdtemp(prefix='pdf_ocr_')
    mat = fitz.Matrix(dpi / 72, dpi / 72)
    paths = []
    for i, page in enumerate(doc):
        out = os.path.join(tmp_dir, f'page_{i+1:04d}.png')
        page.get_pixmap(matrix=mat).save(out)
        paths.append(out)
    doc.close()
    return paths

model.infer_multi(
    tokenizer,
    prompt='<image>Multi page parsing.',
    image_files=pdf_to_images('your_doc.pdf', dpi=300),
    output_path='your/output/dir',
    image_size=1024,
    max_length=32768,
    no_repeat_ngram_size=35, ngram_window=1024,
    save_results=True,
)

vLLM

部署详情请参考官方 vLLM recipe：

Recipe: https://recipes.vllm.ai/baidu/Unlimited-OCR

Docker 镜像

请根据你的 GPU 平台选择以下 Docker 镜像：

Default (CUDA 13.0):

docker pull vllm/vllm-openai:unlimited-ocr

适用于 Hopper GPU（CUDA 12.9）

docker pull vllm/vllm-openai:unlimited-ocr-cu129

SGLang

配置环境（由 uv 管理的虚拟环境）。请先安装本地 SGLang wheel， 然后固定 kernels==0.9.0 的版本，并安装 PyMuPDF 以完成 PDF 转图像：

uv venv --python 3.12
source .venv/bin/activate

uv pip install wheel/sglang-0.0.0.dev11416+g92e8bb79e-py3-none-any.whl
uv pip install kernels==0.11.7
uv pip install pymupdf==1.27.2.2

启动 SGLang 服务：

python -m sglang.launch_server \
    --model baidu/Unlimited-OCR \
    --served-model-name Unlimited-OCR \
    --attention-backend fa3 \
    --page-size 1 \
    --mem-fraction-static 0.8 \
    --context-length 32768 \
    --enable-custom-logit-processor \
    --disable-overlap-schedule \
    --skip-server-warmup \
    --host 0.0.0.0 \
    --port 10000

向兼容 OpenAI 的 API 发送流式请求：

import base64
import json
import os
import tempfile

import fitz
import requests
from sglang.srt.sampling.custom_logit_processor import DeepseekOCRNoRepeatNGramLogitProcessor

server_url = "http://127.0.0.1:10000"

session = requests.Session()
session.trust_env = False


def pdf_to_images(pdf_path, dpi=300):
    doc = fitz.open(pdf_path)
    tmp_dir = tempfile.mkdtemp(prefix="pdf_ocr_")
    mat = fitz.Matrix(dpi / 72, dpi / 72)
    image_paths = []
    for i, page in enumerate(doc):
        image_path = os.path.join(tmp_dir, f"page_{i + 1:04d}.png")
        page.get_pixmap(matrix=mat).save(image_path)
        image_paths.append(image_path)
    doc.close()
    return image_paths


def encode_image(image_path):
    ext = os.path.splitext(image_path)[1].lower()
    mime = "image/jpeg" if ext in (".jpg", ".jpeg") else f"image/{ext.lstrip('.')}"
    with open(image_path, "rb") as f:
        data = base64.b64encode(f.read()).decode("utf-8")
    return {"type": "image_url", "image_url": {"url": f"data:{mime};base64,{data}"}}


def build_content(prompt, image_paths):
    return [{"type": "text", "text": prompt}] + [encode_image(path) for path in image_paths]


def generate(prompt, image_paths, image_mode, ngram_window):
    payload = {
        "model": "Unlimited-OCR",
        "messages": [{"role": "user", "content": build_content(prompt, image_paths)}],
        "temperature": 0,
        "skip_special_tokens": False,
        "images_config": {"image_mode": image_mode},
        "custom_logit_processor": DeepseekOCRNoRepeatNGramLogitProcessor.to_str(),
        "custom_params": {
            "ngram_size": 35,
            "window_size": ngram_window,
        },
        "stream": True,
    }
    response = session.post(
        f"{server_url}/v1/chat/completions",
        headers={"Content-Type": "application/json"},
        data=json.dumps(payload),
        timeout=1200,
        stream=True,
    )
    response.raise_for_status()

    chunks = []
    for line in response.iter_lines(chunk_size=1, decode_unicode=True):
        if not line or not line.startswith("data: "):
            continue
        data = line[len("data: "):]
        if data == "[DONE]":
            break
        event = json.loads(data)
        delta = event["choices"][0].get("delta", {}).get("content", "")
        if delta:
            print(delta, end="", flush=True)
            chunks.append(delta)
    print()
    return "".join(chunks)


# Single image supports two configs: gundam or base. Example below uses gundam.
generate("document parsing.", ["your_image.jpg"], image_mode="gundam", ngram_window=128)

# Multi image (base only)
generate("Multi page parsing.", ["page1.png", "page2.png"], image_mode="base", ngram_window=1024)

# PDF (base only)
generate("Multi page parsing.", pdf_to_images("your_doc.pdf", dpi=300), image_mode="base", ngram_window=1024)

对于批量推理，infer.py 会自动启动 SGLang 服务器，并向图片目录或 PDF 发送并发请求：

# Image directory
python infer.py \
    --image_dir ./examples/images \
    --output_dir ./outputs \
    --concurrency 8 \
    --image_mode gundam

# PDF pages
python infer.py \
    --pdf ./examples/document.pdf \
    --output_dir ./outputs \
    --concurrency 8 \
    --image_mode gundam

常用选项：

--model_dir baidu/Unlimited-OCR   # Local path or Hugging Face model ID
--gpu 0                           # CUDA_VISIBLE_DEVICES value
--server_log ./log/sglang_server.log

可视化

致谢

我们谨此感谢 Deepseek-OCR, Deepseek-OCR-2, PaddleOCR 提供的宝贵模型与思路。

引用

@misc{yin2026unlimitedocrworks,
      title={Unlimited OCR Works}, 
      author={Youyang Yin and Huanhuan Liu and YY and Qunyi Xie and Chaorun Liu and Shiqi Yang and Shaohua Wang and Zhanlong Liu and Hao Zou and Jinyue Chen and Shu Wei and Jingjing Wu and Mingxin Huang and Zhen Wu and Guibin Wang and Tengyu Du and Lei Jia},
      year={2026},
      eprint={2606.23050},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2606.23050}, 
}