magic_pdf/model/doc_analyze_by_custom_model.py · 734ae27bf139b330de981cfeecec78b63bab8b43 · wangsen / MinerU · GitLab

Find file Blame History Permalink

perf(inference): optimize batch processing for different GPU memory sizes · 6116488d
myhloli authored Mar 11, 2025
```
- Set NPUDTCompile to false for better performance on NPU
- Adjust batch ratio
```
6116488d

doc_analyze_by_custom_model.py 7.87 KB