fix(ocr): drop uvicorn workers from 2 to 1

Two workers × ~5 GB Surya model load = ~10 GB required, exceeding the
8 GB memory cap and causing OOM on the first /train call. Two OS
processes also cause model-state divergence after training, contradicting
the single-node constraint documented in ADR-001.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-04-14 09:55:55 +02:00
parent 7b79dc105b
commit 62be895b9e

View File

@@ -23,4 +23,4 @@ COPY . .
EXPOSE 8000
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "2"]
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "1"]