ZPM

使用了这个插件一直转圈

13


[Feature Request]: change model path

1

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What would your feature do ? How do...

just open go-realtime-gui.bat It worked fine with a rtx1650 4g now worked with rtx1660ti 6g,like this is_half:False, device:cuda:0 Input device: 1:麦克风 (2- USB Audio Device) (MME) Output device: 3:扬声器 (2-...

deepseek ocr model cannot be found in local deployment

5

### GPUStack version 0.7.1 ### Operating System & CPU Architecture _No response_ ### GPU L4 ### ▶️ Steps to reproduce root@infer-PVE:/var/lib/gpustack/cache/model_scope/Deepseek/deepseek-ai/DeepSeek-OCR# pwd /var/lib/gpustack/cache/model_scope/Deepseek/deepseek-ai/DeepSeek-OCR root@infer-PVE:/var/lib/gpustack/cache/model_scope/Deepseek/deepseek-ai/DeepSeek-OCR# ls assets conversation.py modeling_deepseekocr.py README.md config.json...

deepseek-ocr deploy failure

1

### ❓ Is your enhancement related to a problem? No suitable workers. Details: Failed to initialize vllm candidates selector: Cannot get pretrained config for model deepseek-ai/DeepSeek-OCR: cannot import name 'LlamaFlashAttention2'...