perf: concurrency improvements for high-volume Excel processing

feat: deploy docling first parser

feat: switch to unsloth gguf runtime

perf: optimize qwen inference path

feat: switch parser to qwen vl

feat: expand parser diagnostics

feat: configure docling accelerator

feat: switch to docling first parser

feat: deploy paddleocr gemini parser

feat: v5.0.0 PaddleOCR-VL-1.5 + Gemini hybrid architecture