Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

add CUDA and ROCm installation instructions

Browse Source
This commit is contained in:
Lincoln Stein 2023-02-07 23:02:45 -05:00
parent 9157da8237
commit 24792eb5da
3 changed files with 99 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/index.md
View File

@ -116,7 +116,7 @@ images in full-precision mode:
`invoke.py` with the `--precision=float32` flag: `invoke.py` with the `--precision=float32` flag:
```bash ```bash
(invokeai) ~/InvokeAI$ python scripts/invoke.py --full_precision (invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
``` ```
## :octicons-package-dependencies-24: Installation ## :octicons-package-dependencies-24: Installation

4
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -118,9 +118,7 @@ experimental versions later.
Terminal, including InvokeAI. This package is provided Terminal, including InvokeAI. This package is provided
directly by Apple. To install, open a terminal window and run `xcode-select --install`. You will get a macOS system popup guiding you through the directly by Apple. To install, open a terminal window and run `xcode-select --install`. You will get a macOS system popup guiding you through the
install. If you already have them installed, you will instead see some install. If you already have them installed, you will instead see some
output in the Terminal advising you that the tools are already installed. output in the Terminal advising you that the tools are already installed. More information can be found at [FreeCode Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
More information can be found at [FreeCode
Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
3. The InvokeAI installer is distributed as a ZIP files. Go to the 3. The InvokeAI installer is distributed as a ZIP files. Go to the
[latest release](https://github.com/invoke-ai/InvokeAI/releases/latest), [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest),

110
docs/installation/030_INSTALL_CUDA_AND_ROCM.md
View File

@ -8,27 +8,111 @@ title: NVIDIA Cuda / AMD ROCm
</figure> </figure>
In order for InvokeAI to run at full speed, you will need a graphics
card with a supported GPU. InvokeAI supports NVidia cards via the CUDA
driver on Windows and Linux, and AMD cards via the ROCm driver on Linux.
## :simple-nvidia: CUDA ## :simple-nvidia: CUDA
### Container Runtime ### Linux and Windows Install
Fancy Site: https://developer.nvidia.com/nvidia-container-runtime If you have used your system for other graphics-intensive tasks, such
as gaming, you may very well already have the CUDA drivers
installed. To confirm, open up a command-line window and type:
GitHub Source: https://github.com/NVIDIA/nvidia-container-runtime/ ```
(where the Fancy Site also links ot xD) nvidia-smi
```
Maybe the most simple way to get InvokeAI running with NVIDIA CUDA will be the official If this command produces a status report on the GPU(s) installed on
NVIDIA Container Runtime (not confirmed, but got told by a friend) that the Runtime even your system, CUDA is installed and you have no more work to do. If
works when you do not have the actual Drivers installed, since it is mounting the GPU instead you get "command not found", or similar, then the driver will
into the Container need to be installed.
We strongly recommend that you install the CUDA Toolkit package
directly from NVIDIA. **Do not try to install Ubuntu's
nvidia-cuda-toolkit package. It is out of date and will cause
conflicts among the NVIDIA driver and binaries.**
Go to [CUDA Toolkit 11.7
Downloads](https://developer.nvidia.com/cuda-11-7-0-download-archive),
and use the target selection wizard to choose your operating system,
hardware platform, and preferred installation method (e.g. "local"
versus "network").
This will provide you with a downloadable install file or, depending
on your choices, a recipe for downloading and running a install shell
script. Be sure to read and follow the full installation instructions.
After an install that seems successful, you can confirm by again
running `nvidia-smi` from the command line.
### Linux Install with a Runtime Container
On Linux systems, an alternative to installing the driver directly on
your system is to run an NVIDIA software container that has the driver
already in place. This is recommended if you are already familiar with
containerization technologies such as Docker.
For downloads and instructions, visit the [NVIDIA CUDA Container
Runtime Site](https://developer.nvidia.com/nvidia-container-runtime)
## :simple-amd: ROCm ## :simple-amd: ROCm
### ROCm-docker ### Linux Install
GitHub Source: https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md AMD GPUs are only supported on Linux platforms due to the lack of a
Windows ROCm driver at the current time. Also be aware that support
for newer AMD GPUs is spotty. Your mileage may vary.
Yeah - I am sorry, but since I am not into PC-Masterrace, I had no better Idea than It is possible that the ROCm driver is already installed on your
looking up if there is a container runtime for ROCm as well xD machine. To test, open up a terminal window and issue the following
command:
So please forgive me, but at least the page isn't empty anymore 🙈 ```
rocm-smi
```
If you get a table labeled "ROCm System Management Interface" the
driver is installed and you are done. If you get "command not found,"
then the driver needs to be installed.
Go to AMD's [ROCm Downloads
Guide](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation_new.html#installation-methods)
and scroll to the _Installation Methods_ section. Find the subsection
for the install method for your preferred Linux distribution, and
issue the commands given in the recipe.
Annoyingly, the official AMD site does not have a recipe for the most
recent version of Ubuntu, 22.04. However, this [community-contributed
recipe](https://novaspirit.github.io/amdgpu-rocm-ubu22/) is reported
to work well.
After installation, please run `rocm-smi` a second time to confirm
that the driver is present and the GPU is recognized. You may need to
do a reboot in order to load the driver.
### Linux Install with a ROCm-docker Container
If you are comfortable with the Docker containerization system, then
you can build a ROCm docker file. The source code and installation
recipes are available
[Here](https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md)
### Torch Installation
When installing torch and torchvision manually with `pip`, remember to provide
the argument `--extra-index-url
https://download.pytorch.org/whl/rocm5.2` as described in the [Manual
Installation Guide](020_INSTALL_MANUAL.md).
This will be done automatically for you if you use the installer
script.
Be aware that the torch machine learning library does not seamlessly
interoperate with all AMD GPUs and you may experience garbled images,
black images, or long startup delays before rendering commences. Most
of these issues can be solved by Googling for workarounds. If you have
a problem and find a solution, please post an
[Issue](https://github.com/invoke-ai/InvokeAI/issues) so that other
users benefit and we can update this document.