liujiachang
liujiachang
I don't find this fie in my data, can you tell me where I can find the tusimple_anno_cache.json, thanks.
每个图片第一次被推理的时候速度都非常慢(10~100秒),第二次被推理时正常(0.5s)。并且第一次推理AICore利用率为0. 代码为PaddleOCR代码,运行ppstructure/predict_system.py。  
**Describe the bug** What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程,最好有截图) 使用python requests.post部署好的接口服务进行流式返回时,返回内容会一次返回一大段,然后等待(大概2~3秒)再次返回一大段。 **Your hardware and system info** Write your system info like CUDA version/system/GPU/torch version here(在这里给出硬件信息和系统信息,如CUDA版本,系统,GPU型号和torch版本等)...
**Describe the bug** What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程,最好有截图) `swift infer --model_type qwen2-vl-7b-instruct --model_id_or_path models/Qwen2-VL-7B-Instruct`  **Your hardware and system info** Write your system info...
### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答? | Is there an...
参考https://docs.primihub.com/docs/advance-usage/deployment/docker-one-in-one 的方式进行部署,未找到仓库。