holycrypto

导出不是很复杂，正在写，插件这块好像麻烦点，如何确保导入导出一致

Any clean solution?

Any updates ?

nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Tue_Aug_15_22:08:11_PDT_2023 Cuda compilation tools, release 12.2, V12.2.140 Build cuda_12.2.r12.2/compiler.33191640_0

I follow this tutorial: [ollama 🆕 - NVIDIA Jetson AI Lab](https://www.jetson-ai-lab.com/tutorial_ollama.html) still got same error output. jetson-containers docker env parameters: ``` CMAKE_CUDA_COMPILER /usr/local/cuda/bin/nvcc CUDA_ARCHITECTURES 87 CUDA_BIN_PATH /usr/local/cuda/bin CUDA_HOME /usr/local/cuda CUDA_NVCC_EXECUTABLE...

> Getting the same issue with the llama3:70b > > ollama run llama3:70b Error: llama runner process no longer running: 1 > > It works fine with other models, so...

# > I have resolved the issue because I made a silly mistake. In simple terms, I had already started the Ollama service in the system before launching the container....

qcloud确实做的很好 https://github.com/TencentCloud/tencentcloud-sdk-ruby

谢谢大佬，可以用了。