perf: concurrency improvements for high-volume Excel processing

fix: Excel tables now output HTML matching Gemini PDF format

feat: add Excel (.xlsx/.xlsm) parsing support via Docling

fix: update docling gemini parser

feat: update granite parser runtime

fix: refine granite parser flow

feat: switch parser to granite docling

feat: deploy docling first parser

fix: constrain llama cuda build

fix: reduce llama build memory

feat: switch to unsloth gguf runtime

perf: optimize qwen inference path

feat: switch parser to qwen vl

fix: restore httpx dependency

feat: simplify parser response flow

fix: refine diagnostic routing output

feat: expand parser diagnostics

feat: add parse routing metadata

feat: expose page-level parse results

fix: refine docling page handling

fix: simplify docling routing logic

fix: refine docling pipeline behavior

feat: configure docling accelerator

fix: update docling routing pipeline

feat: switch to docling first parser

fix: support paddle restructure fallback

feat: deploy paddleocr gemini parser

fix: prevent LaTeX regex from stripping currency dollar signs

fix: table detection, LaTeX cleanup, HTML tables, image filtering

fix: use PaddlePaddle Docker base image (paddle GPU pre-installed)

fix: add pip timeout 600s + retries for Chinese CDN, use Python 3.12 default

fix: use Python 3.12 (Ubuntu 24.04 default), simplify Dockerfile, combine install steps

fix: remove paddle import verification during build (no CUDA available)

fix: remove GPU-dependent pre-download, use restructure_pages for cross-page tables, robust md extraction

fix: use CPU mode for model pre-download during Docker build

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

feat: v4.0.0 — VLM + Gemini 3 Flash hybrid (table pages use Gemini API)

feat: v3.3.1 - disable table re-prompting, add page number cleanup

feat: v3.3.0 - table re-prompting, heading normalization, footer cleanup

feat: v3.3.0 - increase max_tokens to 32768 for wide tables

feat: v3.3.0 - heading normalization, footer cleanup, table fixes

feat: v3.3.0 - DPI 200, post-processing, cross-page dedup

fix: total_mem → total_memory attribute fix for startup

feat: v3.2.1 - remove page markers, fix escaped quotes

feat: v3.2.0 - LaTeX→MD conversion, VLM output cleanup, improved prompt, disable thinking

feat: v3.1.0 - DPI 150, parallel rendering, VLM retry, quality fixes

feat: v3.0.0 VLM-first hybrid architecture — GPU VLM on all pages, Docling TableFormer only on table pages

fix: reduce concurrent VLM workers to 2 to prevent GPU OOM on 30B model

perf: concurrent VLM OCR — process pages in parallel via ThreadPoolExecutor

fix: resolve /parse/url for URLs without file extensions (e.g. arxiv)