dongkuang

Results 7 comments of dongkuang

@WoosukKwon @dcruiz01 I have the same problem.**_and I run nvcc -version,can find cuda is cuda11.8,and I have installed ninja&packaging&setuptools&torch2.0.0&wheel I run it on jetson orin 64G,it's aarch64_**Please help me running...

![nvswtich](https://github.com/NVIDIA/gpu-operator/assets/14137651/6634a142-24c0-4640-b0ff-040ae362fecb) > @dongkuang需要明确的是,您不是通过容器安装驱动程序? > > 你能确认一下你的系统中是否存在这个吗? > > `/proc/driver/nvidia-nvswitch/devices` @tariq1890 Thank you!This directory exists, but there are no files or any content inside,and I am sure I installing the driver...

Today, I saw on the NVIDIA official website that A40 introduces that ultra fast GDDR6 memory can be expanded to 96GB through NVLink.How to install nvswitch?

@WoosukKwon Thank you!It's the result: (myvllm) dongkuang@ubuntu:~$ nvcc -V nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2022 NVIDIA Corporation Built on Wed_Sep_21_10:43:33_PDT_2022 Cuda compilation tools, release 11.8, V11.8.89 Build...

@WoosukKwon Thank you for your help!We want vllm to run with aarch64,it's a wonderful combination!Then if you want to do it too,we are more than willing to cooperate and **supports...

> I solved changed model, because i think not all model are compatible with Animatediff How to do?please help