Add online serving usage with custom logits processor for DeepSeek-OCR

DeepSeek/DeepSeek-OCR.md

@@ -13,6 +13,7 @@ uv pip install -U vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 ```
 
 ## Running DeepSeek-OCR
+### Offline OCR tasks
 In this guide, we demonstrate how to set up DeepSeek-OCR for offline OCR batch processing tasks.
 
 
@@ -64,6 +65,62 @@ for output in model_outputs:
     print(output.outputs[0].text)
 ```
 
+### Online OCR serving
+In this guide, we demonstrate how to set up DeepSeek-OCR for online OCR serving with OpenAI compatible API server.
+
+```bash
+vllm serve deepseek-ai/DeepSeek-OCR --logits_processors vllm.model_executor.models.deepseek_ocr.NGramPerReqLogitsProcessor --no-enable-prefix-caching --mm-processor-cache-gb 0
+```
+
+```python3
+import time
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="EMPTY",
+    base_url="http://localhost:8000/v1",
+    timeout=3600
+)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": "https://ofasys-multimodal-wlcb-3-toshanghai.oss-accelerate.aliyuncs.com/wpf272043/keepme/image/receipt.png"
+                }
+            },
+            {
+                "type": "text",
+                "text": "Free OCR."
+            }
+        ]
+    }
+]
+
+start = time.time()
+response = client.chat.completions.create(
+    model="deepseek-ai/DeepSeek-OCR",
+    messages=messages,
+    max_tokens=2048,
+    temperature=0.0,
+    extra_body={
+        "skip_special_tokens": False,
+        # args used to control custom logits processor
+        "vllm_xargs": {
+            "ngram_size": 30,
+            "window_size": 90,
+            # whitelist: <td>, </td>
+            "whitelist_token_ids": [128821, 128822],
+        },
+    },
+)
+print(f"Response costs: {time.time() - start:.2f}s")
+print(f"Generated text: {response.choices[0].message.content}")
+```
+
 ## Configuration Tips
 - **It's important to use the custom logits processor** along with the model for the optimal OCR and markdown generation performance.
 - Unlike multi-turn chat use cases, we do not expect OCR tasks to benefit significantly from prefix caching or image reuse, therefore it's recommended to turn off these features to avoid unnecessary hashing and caching.