Hacker News 热门（buzzing.cc 中文翻译）

精选

AI 编辑部评分，满分 100

无限制OCR：单次长时域解析

2026-06-23 21:32· 45天前· ingve

AI 导读

Unlimited OCR 是一个托管在 GitHub 的项目，实现单次长时域解析（One-Shot Long-Horizon Parsing），旨在一次性处理长时间跨度的 OCR 任务。

推荐理由

百度把能处理超长文档的 OCR 系统开源了，宣称一次推理搞定整份文件，做发票、合同、档案数字化的可以马上跑起来试试。

正文 · AI 翻译

无限OCR功能

欢迎进入一次性长周期解析时代。

发布

[2026/07/03] 🤝 感谢百度云团队的支持。我们的模型现已上线百度云。
[2026/06/28] 🤝 感谢vLLM社区和郭天宇的支持，我们的模型现已支持vLLM推理。
[2026/06/24] 🤝 感谢AK为我们创建了演示。该演示现已在Hugging Face Spaces上线。
[2026/06/23] 📄 我们的论文现已在arXiv上发布。
[2026/06/23] 🤝 感谢ModelScope社区的支持。我们的模型现已上线ModelScope。
[2026/06/22] 🚀 我们推出Unlimited-OCR，旨在将Deepseek-OCR向前推进一步。

推理

Transformers

使用Huggingface Transformers在NVIDIA GPU上进行推理。在python 3.12.3 + CUDA12.9环境下测试通过的需求：

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

请参考官方vLLM配方了解部署详情：

Docker镜像

根据您的GPU平台使用以下Docker镜像：

默认（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

设置环境（uv管理的虚拟环境）。先安装本地SGLang wheel包，然后固定kernels==0.9.0版本，并安装PyMuPDF用于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服务器：

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，并向图像目录或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

实用选项：

--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

我们感谢Deepseek-OCR、Deepseek-OCR-2、PaddleOCR提供的宝贵模型和思路。

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}, 
}

多模态开源/仓库

来源：Hacker News 热门（buzzing.cc 中文翻译） · github.com

导出 Markdown