Trieu Viet Hung
Trieu Viet Hung
I have the same problem when serving with 5 models. This is my current hardware: CPU: I5-10400F GPU: RTX 3060 12GB VRAM RAM: 8 GB I tested with 2 models,...
I faced this issue, you need to install CUDA 11.8 and corresponding torch version with CUDA 11.8.
Waiting for the updated instruction.
> Hi @hungtrieu07 Yes, TorchServe supports multi model endpoints > > You can refer to this https://github.com/pytorch/serve/pull/3040/files#diff-b70d3a47c15879d308451b54821682f1d63518db732881b434c4110d9ca7a767R44 Hi @agunapal, I'm coding an python app using PyQT5, like an surveilance camera...
Can you try ```curl http://127.0.0.1:8080/ping``` ? It will return Status equals Healthy if your service run smoothly, else return Unhealthy
This is my ```config.properties``` file, you can refer to it: ``` inference_address=http://0.0.0.0:8080 management_address=http://0.0.0.0:8081 metrics_address=http://0.0.0.0:8082 load_models=all install_py_dep_per_model=true model_store=model-store models={\ "FaceDetection": {\ "1.0": {\ "defaultVersion": true,\ "marName": "FaceDetection.mar",\ "minWorkers": 1,\ "maxWorkers": 1,\...
> It could be a version issue with the Cython library. Try using a lower version: `pip install cython==0.29.36` This solved my problem when install mmdetection 2.1.0
> Hello, I don't understand. If I reproduce the code to upload documents to the bucket from the command console, the files are uploaded to Firebase without problems. On the...
> Hi @hungtrieu07 Do you require further assistance with this case, please? Thanks! Thanks for your reply, I'm fixed that error and now the app run smoothly.
Cursor have been recognized the Python enviroment, but it got this error. The code snippet still run smoothly.