Bureaucrats, cc_docs_admin, cc_staff
2,879
edits
Using cloud GPUs: Difference between revisions
Marked this version for translation
(update to more recent OS versions) Tag: Reverted |
(Marked this version for translation) Tag: Reverted |
||
| Line 2: | Line 2: | ||
<translate> | <translate> | ||
<!--T:31--> | |||
This page describes how to | This page describes how to | ||
* allocate virtual GPU (vGPU) resources to a virtual machine (VM), | * allocate virtual GPU (vGPU) resources to a virtual machine (VM), | ||
| Line 9: | Line 10: | ||
If you choose to install the toolkit directly from NVIDIA, please ensure that the vGPU driver is not overwritten with the one from the CUDA package. | If you choose to install the toolkit directly from NVIDIA, please ensure that the vGPU driver is not overwritten with the one from the CUDA package. | ||
== Supported flavors == | == Supported flavors == <!--T:32--> | ||
<!--T:3--> | <!--T:3--> | ||
| Line 18: | Line 19: | ||
* g1-16gb-c8-40gb | * g1-16gb-c8-40gb | ||
== Preparation of a VM running AlmaLinux 9 == | == Preparation of a VM running AlmaLinux 9 == <!--T:33--> | ||
<!--T:34--> | |||
Once the VM is available, make sure to update the OS to the latest available software, including the kernel. | Once the VM is available, make sure to update the OS to the latest available software, including the kernel. | ||
Then, reboot the VM to have the latest kernel running. | Then, reboot the VM to have the latest kernel running. | ||
<!--T:35--> | |||
To have access to the [https://en.wikipedia.org/wiki/Dynamic_Kernel_Module_Support DKMS package], the [https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm EPEL repository] is required. | To have access to the [https://en.wikipedia.org/wiki/Dynamic_Kernel_Module_Support DKMS package], the [https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm EPEL repository] is required. | ||
<!--T:36--> | |||
AlmaLinux 9 has by default a faulty <code>nouveau</code> driver which crashes the kernel as soon as the <code>nvidia</code> driver is mounted. | AlmaLinux 9 has by default a faulty <code>nouveau</code> driver which crashes the kernel as soon as the <code>nvidia</code> driver is mounted. | ||
The VM needs a few extra steps to prevent the loading of the nouveau driver when the system boots. | The VM needs a few extra steps to prevent the loading of the nouveau driver when the system boots. | ||
| Line 36: | Line 40: | ||
<translate> | <translate> | ||
<!--T:37--> | |||
After the reboot of the VM, the Arbutus vGPU Cloud repository needs to be installed. | After the reboot of the VM, the Arbutus vGPU Cloud repository needs to be installed. | ||
| Line 43: | Line 48: | ||
<translate> | <translate> | ||
<!--T:38--> | |||
The next step is to install the vGPU packages, which will install the required driver and user-space tools. | The next step is to install the vGPU packages, which will install the required driver and user-space tools. | ||
| Line 51: | Line 57: | ||
<translate> | <translate> | ||
<!--T:39--> | |||
After a successful installation, <code>nvidia-smi</code> can be used to verify the proper functionality. | After a successful installation, <code>nvidia-smi</code> can be used to verify the proper functionality. | ||
| Line 79: | Line 86: | ||
<translate> | <translate> | ||
== Preparation of a VM running AlmaLinux 8 == | == Preparation of a VM running AlmaLinux 8 == <!--T:40--> | ||
<!--T:41--> | |||
Once the VM is available, make sure to update the OS to the latest available software, including the kernel. Then, reboot the VM to have the latest kernel running. | Once the VM is available, make sure to update the OS to the latest available software, including the kernel. Then, reboot the VM to have the latest kernel running. | ||
To have access to the [https://en.wikipedia.org/wiki/Dynamic_Kernel_Module_Support DKMS package], the EPEL repository is required. | To have access to the [https://en.wikipedia.org/wiki/Dynamic_Kernel_Module_Support DKMS package], the EPEL repository is required. | ||
| Line 90: | Line 98: | ||
<translate> | <translate> | ||
<!--T:42--> | |||
After the reboot of the VM, the Arbutus vGPU Cloud repository needs to be installed. | After the reboot of the VM, the Arbutus vGPU Cloud repository needs to be installed. | ||
| Line 98: | Line 107: | ||
<translate> | <translate> | ||
<!--T:43--> | |||
The next step is to install the vGPU packages, which will install the required driver and user-space tools. | The next step is to install the vGPU packages, which will install the required driver and user-space tools. | ||
</translate> | </translate> | ||
| Line 105: | Line 115: | ||
<translate> | <translate> | ||
<!--T:44--> | |||
After a successful installation, <code>nvidia-smi</code> can be used to verify the proper functionality. | After a successful installation, <code>nvidia-smi</code> can be used to verify the proper functionality. | ||
| Line 132: | Line 143: | ||
<translate> | <translate> | ||
== Preparation of a VM running Debian 11 == | == Preparation of a VM running Debian 11 == <!--T:45--> | ||
Ensure that the latest packages are installed and the system has been booted with the latest stable kernel, as <b>DKMS</b> will request the latest one available from the Debian repositories. | Ensure that the latest packages are installed and the system has been booted with the latest stable kernel, as <b>DKMS</b> will request the latest one available from the Debian repositories. | ||
| Line 141: | Line 152: | ||
<translate> | <translate> | ||
<!--T:46--> | |||
After a successful reboot, the system should have the latest available kernel running and the repository can be installed, by installing the <code>arbutus-cloud-repo</code> package. | After a successful reboot, the system should have the latest available kernel running and the repository can be installed, by installing the <code>arbutus-cloud-repo</code> package. | ||
This package also contains the gpg key all packages are signed with. | This package also contains the gpg key all packages are signed with. | ||
| Line 151: | Line 163: | ||
<translate> | <translate> | ||
<!--T:47--> | |||
Update the local apt cache and install the vGPU packages: | Update the local apt cache and install the vGPU packages: | ||
| Line 183: | Line 196: | ||
<translate> | <translate> | ||
== Preparation of a VM running Debian 12 == | == Preparation of a VM running Debian 12 == <!--T:48--> | ||
Ensure that the latest packages are installed and the system has been booted with the latest stable kernel, as <b>DKMS</b> will request the latest one available from the Debian repositories. | Ensure that the latest packages are installed and the system has been booted with the latest stable kernel, as <b>DKMS</b> will request the latest one available from the Debian repositories. | ||
| Line 192: | Line 205: | ||
<translate> | <translate> | ||
<!--T:49--> | |||
After a successful reboot, the system should have the latest available kernel running and the repository can be installed, by installing the <code>arbutus-cloud-repo</code> package. | After a successful reboot, the system should have the latest available kernel running and the repository can be installed, by installing the <code>arbutus-cloud-repo</code> package. | ||
This package also contains the gpg key all packages are signed with. | This package also contains the gpg key all packages are signed with. | ||
| Line 202: | Line 216: | ||
<translate> | <translate> | ||
<!--T:50--> | |||
Update the local apt cache and install the vGPU packages: | Update the local apt cache and install the vGPU packages: | ||
| Line 234: | Line 249: | ||
<translate> | <translate> | ||
== Preparation of a VM running Ubuntu 22 == | == Preparation of a VM running Ubuntu 22 == <!--T:51--> | ||
Ensure that the OS is up to date, that all the latest patches are installed, and that the latest stable kernel is running. | Ensure that the OS is up to date, that all the latest patches are installed, and that the latest stable kernel is running. | ||
| Line 243: | Line 258: | ||
<translate> | <translate> | ||
<!--T:52--> | |||
After a successful reboot, the system should have the latest available kernel running. | After a successful reboot, the system should have the latest available kernel running. | ||
Now the repository can be installed by installing the <code>arbutus-cloud-repo</code> package. | Now the repository can be installed by installing the <code>arbutus-cloud-repo</code> package. | ||
| Line 254: | Line 270: | ||
<translate> | <translate> | ||
<!--T:53--> | |||
Update the local apt cache and install the vGPU packages: | Update the local apt cache and install the vGPU packages: | ||
</translate> | </translate> | ||
| Line 261: | Line 278: | ||
<translate> | <translate> | ||
<!--T:54--> | |||
If your installation was successful, the vGPU will be accessible and licensed. | If your installation was successful, the vGPU will be accessible and licensed. | ||
| Line 289: | Line 307: | ||
<translate> | <translate> | ||
== Preparation of a VM running Ubuntu 20 == | == Preparation of a VM running Ubuntu 20 == <!--T:55--> | ||
Ensure that the OS is up to date, that all the latest patches are installed, and that the latest stable kernel is running. | Ensure that the OS is up to date, that all the latest patches are installed, and that the latest stable kernel is running. | ||
| Line 298: | Line 316: | ||
<translate> | <translate> | ||
<!--T:56--> | |||
After a successful reboot, the system should have the latest available kernel running. | After a successful reboot, the system should have the latest available kernel running. | ||
Now the repository can be installed by installing the <code>arbutus-cloud-repo</code> package. | Now the repository can be installed by installing the <code>arbutus-cloud-repo</code> package. | ||
| Line 309: | Line 328: | ||
<translate> | <translate> | ||
<!--T:57--> | |||
Update the local apt cache and install the vGPU packages: | Update the local apt cache and install the vGPU packages: | ||
</translate> | </translate> | ||
| Line 316: | Line 336: | ||
<translate> | <translate> | ||
<!--T:58--> | |||
If your installation was successful, the vGPU will be accessible and licensed. | If your installation was successful, the vGPU will be accessible and licensed. | ||