40 lines
551 B
Markdown
40 lines
551 B
Markdown
```shell
|
|
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb
|
|
sudo dpkg -i cuda-keyring_1.1-1_all.deb
|
|
sudo apt-get update
|
|
sudo apt-get -y install cuda-toolkit-12-8
|
|
sudo apt-get install -y cuda-drivers
|
|
```
|
|
|
|
```shell
|
|
nvidia-smi
|
|
```
|
|
|
|
```shell
|
|
nvcc -V
|
|
```
|
|
|
|
```shell
|
|
conda create --name test-vllm-gpt-oss-20b-crash python=3.12 -y
|
|
```
|
|
|
|
```shell
|
|
conda activate test-vllm-gpt-oss-20b-crash
|
|
```
|
|
|
|
```shell
|
|
model
|
|
```
|
|
|
|
```shell
|
|
python --version
|
|
```
|
|
|
|
```shell
|
|
pip install vllm
|
|
```
|
|
|
|
下载 gpt-oss-20b 模型
|
|
|
|
|