Repository Issue Activity (beta)

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

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

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

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

#225 Add TSV or CSV export support

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

#233 GLMocr可以运行在atlas 300i duo卡上面吗？

#232 昇腾卡上用sglang启动无法开启mtp

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

#229 Verify evals on Papers with Code

#228 用红框crop部分图像做推理，，，结果有点差

#227 Cannot run on aarch64 Linux

#149 能否给出论文中的Nanonets-KIE 和 Handwritten-KIE 数据集的来源

#226 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

#224 Receipt KIE是哪个榜单

#222 本地部署的GLM-OCR，不使用api_key情况下，如何进行文档结构化解析

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

#64 [question] local files

#218 [Performance] GLM-OCR MTP: ~1.5x speedup on eager path but ~0.62x on default CUDA Graph path (OCRBench)

#116 昇腾910b使用vllm部署，精度劣化严重

#175 GLM-OCR much slower than PP-OCR-VL on T4 (16s vs 2–3s per page), possible misconfiguration?

#212 [Bug] Low OCR accuracy for Cantonese / Hong Kong Traditional Chinese characters

#211 服务器自部署OCR模型并使用的SDK构造流水线问题

#157 The decoder prompt contains a(n) image item with length 6132, which exceeds the pre-allocated encoder cache size 6084

#209 使用官网OCR文档解析服务，PDF出现漏检情况，部分区域没有检测到！