# vLLM backend tuning for paddleocr genai_server
# Docs: https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PaddleOCR-VL.html#331-server-side-parameter-adjustment
gpu-memory-utilization: 0.6
max-num-seqs: 4
enforce-eager: true
max-model-len: 2048
max-num-batched-tokens: 2048