README

📥 Model Download |
  📄 Paper Link |
  📄 Arxiv Paper Link |




  DeepSeek-OCR: Contexts Optical Compression







Explore the boundaries of visual-text compression.       


 Release
- [2026/01/27]🚀🚀🚀🚀🚀🚀 We present DeepSeek-OCR2
- [2025/10/23]🚀🚀🚀 DeepSeek-OCR is now officially supported in upstream vLLM. Thanks to the vLLM team for their help.
- [2025/10/20]🚀🚀🚀 We release DeepSeek-OCR, a model to investigate the role of vision encoders from an LLM-centric viewpoint.

 Contents
- Install
- vLLM Inference
- Transformers Inference
  




 Install
Our environment is cuda11.8+torch2.6.0.
1. Clone this repository and navigate to the DeepSeek-OCR folder
bash
git clone https://github.com/deepseek-ai/DeepSeek-OCR.git

2. Conda
Shell
conda create -n deepseek-ocr python=3.12.9 -y
conda activate deepseek-ocr

3. Packages

- download the vllm-0.8.5 whl 
Shell
pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu118
pip install vllm-0.8.5+cu118-cp38-abi3-manylinux1_x86_64.whl
pip install -r requirements.txt
pip install flash-attn==2.7.3 --no-build-isolation

Note: if you want vLLM and transformers codes to run in the same environment, you don't need to worry about this installation error like: vllm 0.8.5+cu118 requires transformers=4.51.1

 vLLM-Inference
- VLLM:
Note: change the INPUT_PATH/OUTPUT_PATH and other settings in the DeepSeek-OCR-master/DeepSeek-OCR-vllm/config.py
Shell
cd DeepSeek-OCR-master/DeepSeek-OCR-vllm

1. image: streaming output
Shell
python run_dpsk_ocr_image.py

2. pdf: concurrency ~2500tokens/s(an A100-40G)
Shell
python run_dpsk_ocr_pdf.py

3. batch eval for benchmarks
Shell
python run_dpsk_ocr_eval_batch.py


[2025/10/23] The version of upstream vLLM:

shell
uv venv
source .venv/bin/activate
 Until v0.11.1 release, you need to install vLLM from nightly build
uv pip install -U vllm --pre --extra-index-url https://wheels.vllm.ai/nightly


python
from vllm import LLM, SamplingParams
from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor
from PIL import Image

 Create model instance
llm = LLM(
    model="deepseek-ai/DeepSeek-OCR",
    enable_prefix_caching=False,
    mm_processor_cache_gb=0,
    logits_processors=[NGramPerReqLogitsProcessor]
)

 Prepare batched input with your image file
image_1 = Image.open("path/to/your/image_1.png").convert("RGB")
image_2 = Image.open("path/to/your/image_2.png").convert("RGB")
prompt = "\nFree OCR."

model_input = [
    {
        "prompt": prompt,
        "multi_modal_data": {"image": image_1}
    },
    {
        "prompt": prompt,
        "multi_modal_data": {"image": image_2}
    }
]

sampling_param = SamplingParams(
            temperature=0.0,
            max_tokens=8192,
             ngram logit processor args
            extra_args=dict(
                ngram_size=30,
                window_size=90,
                whitelist_token_ids={128821, 128822},   whitelist: , 
            ),
            skip_special_tokens=Fal