GLM-OCR · Issues· 58 open

Decimal separators (comma) lost in numeric cells when OCRing an isolated crop of a table region vs. full-page OCR

Table footer/summary rows missing from OCR output (rows present in source, absent from table markup)

How to train for a different language?

GLM-OCR repeats OCR output unless a stop sequence is configured and for some images if configured then also repeats the OCR

Apache-2.0 declaration conflicts with mandatory AGPL dependency (pymupdf)

Add TSV or CSV export support

png图片输入无法保存出jpg / RGBA images fail to save as JPEG

GLMocr可以运行在atlas 300i duo卡上面吗？

昇腾卡上用sglang启动无法开启mtp

vLLM serve fails on WSL2 — EngineCore segfault during multimodal encoder initialization

Verify evals on Papers with Code

用红框crop部分图像做推理，，，结果有点差

Cannot run on aarch64 Linux

Handwritten-KIE评测集复现时得分仅64+，和论文中差异较大，请问是有什么优化策略吗

部署Flask 服务后，版面分析/glmocr/parse接口如何支持并发？