What's Changed

• perf(model): optimize model initialization by @myhloli in https://github.com/opendatalab/MinerU/pull/1198
• fix: update notify by @dt-yy in https://github.com/opendatalab/MinerU/pull/1201
• fix(model): simplify model initialization logic by @myhloli in https://github.com/opendatalab/MinerU/pull/1207
• feat: update test case by @dt-yy in https://github.com/opendatalab/MinerU/pull/1209
• build(deps): specify minimum version for ultralytics by @myhloli in https://github.com/opendatalab/MinerU/pull/1212
• Refactor/add user api by @icecraft in https://github.com/opendatalab/MinerU/pull/1178
• fix(dict2md): add space for inline equations in CJK contexts by @myhloli in https://github.com/opendatalab/MinerU/pull/1222
• fix: 1. ocr txt mode error 2. lose pdf_parse_type field by @icecraft in https://github.com/opendatalab/MinerU/pull/1224
• fix: add parse_pdf_type and version by @icecraft in https://github.com/opendatalab/MinerU/pull/1228
• fix: unicode decode error by @icecraft in https://github.com/opendatalab/MinerU/pull/1231
• fix(detect_invalid_chars):fix the stack error caused by multiple memory releases in PyMuPDF by @myhloli in https://github.com/opendatalab/MinerU/pull/1252
• fix: dup classify pdf type by @icecraft in https://github.com/opendatalab/MinerU/pull/1258
• feat(layout): improve layout detection for DocLayout_YOLO model by @myhloli in https://github.com/opendatalab/MinerU/pull/1259
• refactor(draw_bbox): remove redundant '_line_sort' suffix from output filename by @myhloli in https://github.com/opendatalab/MinerU/pull/1263
• build(docker): add torch and torchvision dependencies by @myhloli in https://github.com/opendatalab/MinerU/pull/1264

Full Changelog: https://github.com/opendatalab/MinerU/compare/magic_pdf-0.10.5-released...magic_pdf-0.10.6-released