smithlai

Can I understand that as of now, only Pose Detection is supported with GPU acceleration?

Thank you dusty, And there is one more issue there. I tried to rebuild my container with `./build -n my_contatiner langchain` or `./build -n my_contatiner llama_cpp` but always failed here...

> Hi @smithlai, did you set your default docker runtime to nvidia? This enables CUDA to be used during the builds. > > https://github.com/dusty-nv/jetson-containers/blob/master/docs/setup.md#docker-default-runtime My apologies! I did't noticed that...

> @smithlai 可否提供一下环境中torch、transformers的版本以及所使用模型的信息呢？ 不好意思回晚了 ### environment: ``` Anaconda (python 3.10.14) ``` ### package ```python torch==2.4.0+cu124 torchaudio==2.4.0+cu124 torchvision==0.19.0+cu124 transformers==4.43.3 ``` ### Model ```python model = AutoModelForSequenceClassification.from_pretrained("hfl/rbt3") ``` ### error ```python ---------------------------------------------------------------------------...

Me, too. Device: Pixel 7 Pro Android14 Model: gemma-2b-it-cpu-int4.bin / gemma-1.1-2b-it-cpu-int4.bin However, the gemma-2b-it-gpu-int4.bin works