Suya OCR API — vLLM-backed, OpenAI-compatible OCR service

FastAPI service wrapping the Surya-OCR-2 model (datalab-to) served through vLLM:
legacy /v1/api/ai/* endpoints, an OpenAI-compatible /v1/chat/completions endpoint,
a coalescing request batcher, a local OCR CLI, Docker packaging, multilingual
example outputs, and quantization/concurrency benchmarks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

surya/common/load.py

@@ -0,0 +1,25 @@
+from typing import Optional, Any
+
+import torch
+
+from surya.settings import settings
+
+
+class ModelLoader:
+    def __init__(self, checkpoint: Optional[str] = None):
+        self.checkpoint = checkpoint
+
+    def model(
+        self,
+        device: torch.device | str | None = settings.TORCH_DEVICE_MODEL,
+        dtype: Optional[torch.dtype | str] = settings.MODEL_DTYPE,
+        attention_implementation: Optional[str] = None,
+    ) -> Any:
+        raise NotImplementedError()
+
+    def processor(
+        self,
+        device: torch.device | str | None = settings.TORCH_DEVICE_MODEL,
+        dtype: Optional[torch.dtype | str] = settings.MODEL_DTYPE,
+    ) -> Any:
+        raise NotImplementedError()