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>

tests/test_resolve_max_workers.py

@@ -0,0 +1,13 @@
+from surya.inference.backends.openai_client import resolve_max_workers
+
+
+def test_caps_at_max_inflight():
+    assert resolve_max_workers(batch_len=160, max_inflight=16) == 16
+
+
+def test_uses_batch_len_when_smaller():
+    assert resolve_max_workers(batch_len=4, max_inflight=16) == 4
+
+
+def test_never_below_one():
+    assert resolve_max_workers(batch_len=0, max_inflight=16) == 1