git clone https://github.com/deepseek-ai/DeepSeek-OCR.git
cd DeepSeek-OCR

conda create -n deepseek-ocr python=3.12.9 -y
conda activate deepseek-ocr

# Install PyTorch with CUDA 11.8
pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 \
  --index-url https://download.pytorch.org/whl/cu118

# Download vllm-0.8.5 whl from https://github.com/vllm-project/vllm/releases/tag/v0.8.5
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

uv venv
source .venv/bin/activate
uv pip install -U vllm --pre --extra-index-url https://wheels.vllm.ai/nightly

from huggingface_hub import snapshot_download
snapshot_download(repo_id="deepseek-ai/DeepSeek-OCR")

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

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

image = Image.open("document.png").convert("RGB")
prompt = "<image>\nFree OCR."

sampling_params = SamplingParams(
    temperature=0.0,
    max_tokens=8192,
    extra_args=dict(
        ngram_size=30,
        window_size=90,
        whitelist_token_ids={128821, 128822},  # <td>, </td> for table support
    ),
    skip_special_tokens=False,
)

outputs = llm.generate(
    [{"prompt": prompt, "multi_modal_data": {"image": image}}],
    sampling_params
)

print(outputs[0].outputs[0].text)

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

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

image_paths = ["page1.png", "page2.png", "page3.png"]
prompt = "<image>\n<|grounding|>Convert the document to markdown. "

model_input = [
    {
        "prompt": prompt,
        "multi_modal_data": {"image": Image.open(p).convert("RGB")}
    }
    for p in image_paths
]

sampling_params = SamplingParams(
    temperature=0.0,
    max_tokens=8192,
    extra_args=dict(
        ngram_size=30,
        window_size=90,
        whitelist_token_ids={128821, 128822},
    ),
    skip_special_tokens=False,
)

outputs = llm.generate(model_input, sampling_params)

for path, output in zip(image_paths, outputs):
    print(f"=== {path} ===")
    print(output.outputs[0].text)

cd DeepSeek-OCR-master/DeepSeek-OCR-vllm
# Edit config.py: set INPUT_PATH, OUTPUT_PATH, model path, etc.
python run_dpsk_ocr_pdf.py   # ~2500 tokens/s on A100-40G

cd DeepSeek-OCR-master/DeepSeek-OCR-vllm
python run_dpsk_ocr_eval_batch.py

import os
import torch
from transformers import AutoModel, AutoTokenizer

os.environ["CUDA_VISIBLE_DEVICES"] = "0"

model_name = "deepseek-ai/DeepSeek-OCR"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(
    model_name,
    _attn_implementation="flash_attention_2",
    trust_remote_code=True,
    use_safetensors=True,
)
model = model.eval().cuda().to(torch.bfloat16)

# Document to markdown
res = model.infer(
    tokenizer,
    prompt="<image>\n<|grounding|>Convert the document to markdown. ",
    image_file="document.jpg",
    output_path="./output/",
    base_size=1024,
    image_size=640,
    crop_mode=True,
    save_results=True,
    test_compress=True,
)
print(res)

cd DeepSeek-OCR-master/DeepSeek-OCR-hf
python run_dpsk_ocr.py

PROMPTS = {
    "document_markdown": "<image>\n<|grounding|>Convert the document to markdown. ",
    "ocr_image":         "<image>\n<|grounding|>OCR this image. ",
    "free_ocr":          "<image>\nFree OCR. ",
    "parse_figure":      "<image>\nParse the figure. ",
    "describe":          "<image>\nDescribe this image in detail. ",
    "rec":               "<image>\nLocate <|ref|>{target}<|/ref|> in the image. ",
}

# Transformers: control resolution via infer() params
res = model.infer(
    tokenizer,
    prompt=prompt,
    image_file="image.jpg",
    base_size=1024,   # 512, 640, 1024, or 1280
    image_size=640,   # patch size for dynamic mode
    crop_mode=True,   # True = Gundam dynamic resolution
)

# Key config fields (example)
MODEL_PATH = "deepseek-ai/DeepSeek-OCR"   # or local path
INPUT_PATH = "/data/input_images/"
OUTPUT_PATH = "/data/output/"
TENSOR_PARALLEL_SIZE = 1                   # GPUs for tensor parallelism
MAX_TOKENS = 8192
TEMPERATURE = 0.0
NGRAM_SIZE = 30
WINDOW_SIZE = 90

import os
from pathlib import Path
from PIL import Image
from vllm import LLM, SamplingParams
from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor

def batch_ocr(image_dir: str, output_dir: str, prompt: str = "<image>\nFree OCR."):
    Path(output_dir).mkdir(parents=True, exist_ok=True)
    
    llm = LLM(
        model="deepseek-ai/DeepSeek-OCR",
        enable_prefix_caching=False,
        mm_processor_cache_gb=0,
        logits_processors=[NGramPerReqLogitsProcessor],
    )
    sampling_params = SamplingParams(
        temperature=0.0,
        max_tokens=8192,
        extra_args=dict(ngram_size=30, window_size=90, whitelist_token_ids={128821, 128822}),
        skip_special_tokens=False,
    )
    
    image_files = list(Path(image_dir).glob("*.png")) + list(Path(image_dir).glob("*.jpg"))
    
    inputs = [
        {"prompt": prompt, "multi_modal_data": {"image": Image.open(f).convert("RGB")}}
        for f in image_files
    ]
    
    outputs = llm.generate(inputs, sampling_params)
    
    for img_path, output in zip(image_files, outputs):
        out_file = Path(output_dir) / (img_path.stem + ".txt")
        out_file.write_text(output.outputs[0].text)
        print(f"Saved: {out_file}")

batch_ocr("/data/scans/", "/data/results/")

import fitz  # PyMuPDF
from PIL import Image
from io import BytesIO
from vllm import LLM, SamplingParams
from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor

def pdf_to_markdown(pdf_path: str) -> list[str]:
    doc = fitz.open(pdf_path)
    llm = LLM(
        model="deepseek-ai/DeepSeek-OCR",
        enable_prefix_caching=False,
        mm_processor_cache_gb=0,
        logits_processors=[NGramPerReqLogitsProcessor],
    )
    sampling_params = SamplingParams(
        temperature=0.0,
        max_tokens=8192,
        extra_args=dict(ngram_size=30, window_size=90, whitelist_token_ids={128821, 128822}),
        skip_special_tokens=False,
    )
    
    prompt = "<image>\n<|grounding|>Convert the document to markdown. "
    inputs = []
    for page in doc:
        pix = page.get_pixmap(dpi=150)
        img = Image.open(BytesIO(pix.tobytes("png"))).convert("RGB")
        inputs.append({"prompt": prompt, "multi_modal_data": {"image": img}})
    
    outputs = llm.generate(inputs, sampling_params)
    return [o.outputs[0].text for o in outputs]

pages = pdf_to_markdown("report.pdf")
full_markdown = "\n\n---\n\n".join(pages)
print(full_markdown)

import torch
from transformers import AutoModel, AutoTokenizer

model_name = "deepseek-ai/DeepSeek-OCR"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(
    model_name,
    _attn_implementation="flash_attention_2",
    trust_remote_code=True,
    use_safetensors=True,
).eval().cuda().to(torch.bfloat16)

target = "Total Amount"
prompt = f"<image>\nLocate <|ref|>{target}<|/ref|> in the image. "

res = model.infer(
    tokenizer,
    prompt=prompt,
    image_file="invoice.jpg",
    output_path="./output/",
    base_size=1024,
    image_size=640,
    crop_mode=False,
    save_results=True,
)
print(res)  # Returns bounding box / location info

# Ensure torch is installed before flash-attn
pip install flash-attn==2.7.3 --no-build-isolation

from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor
llm = LLM(..., logits_processors=[NGramPerReqLogitsProcessor])

whitelist_token_ids={128821, 128822}  # <td> and </td>

llm = LLM(
    model="deepseek-ai/DeepSeek-OCR",
    tensor_parallel_size=4,  # number of GPUs
    enable_prefix_caching=False,
    mm_processor_cache_gb=0,
    logits_processors=[NGramPerReqLogitsProcessor],
)

DeepSeek-OCR-master/
├── DeepSeek-OCR-vllm/
│   ├── config.py                  # vLLM configuration
│   ├── run_dpsk_ocr_image.py      # Single image inference
│   ├── run_dpsk_ocr_pdf.py        # PDF batch inference
│   └── run_dpsk_ocr_eval_batch.py # Benchmark evaluation
└── DeepSeek-OCR-hf/
    └── run_dpsk_ocr.py            # HuggingFace Transformers inference