2023-07 - I have composed this collection of instructions as they are my notes. I use to setup my own Linux system with AMD parts. I've gone over these doing many re-installs to get them all right. This is what I had hoped to find when I had search for install instructions - so I'm sharing them in the hopes that they save time for other people. There may be in here extra parts that aren't needed but this works for me. Originally text, with comments like a shell script that I cut and paste.
2023-09-09 - I had a report that this doesn't work in virtual machines (virtualbox) as the system there cannot see the hardware, it can't load drivers, etc. While this is not a guide about Windows, Windows users may find it more helpful to try DirectML - https://rocm.docs.amd.com/en/latest/deploy/windows/quick_start.html / https://github.com/lshqqytiger/stable-diffusion-webui-directml
[ ... updates abridged ... ]
2023-12-18 - ROCm 6 is out, so there's an updated guide for that here - https://github.com/nktice/AMD-AI/blob/main/ROCm6.0.md
2023-12-18 - This document has been updated for ROCm 5.7.3
2024-03-06 - Updates becauase ROCm 5.7 is the current stable version supported by PyTorch, as such I'm making those instructions the main instructions offered here. They were in a separate file, those contents are still there in case someone links to it, and for posterity once things move on. Minor updates here to refer to the latest versions of some files.
2024-03-07 - This page updated to call standard stable default versions ( rather than development versions... ) Note that ROCm 5.7 series still has the issue where loading across multiple GPUs with different architectures will appear to work, but outputs gibberish.
2024-04-24 - Updates to deal with new versions of Python, and Bitsandbytes. Ubuntu 24.04 does not yet work with amdgpu-dkms.
Ubuntu 22.04 works great on Radeon 6900 XT video cards, but does not support 7900XTX cards as they came out later Ubuntu 23.04 is newer but has issues with some of the tools. So the notes below should work on either system, unless commented.
At this point we assume you've done the system install and you know what that is, have a user, root, etc.
# update system packages
sudo apt update -y && sudo apt upgrade -y #turn on devel and sources.
sudo apt-add-repository -y -s -s
sudo apt install -y "linux-headers-$(uname -r)" \
"linux-modules-extra-$(uname -r)"Some things may require older versions of python, so we need to add jammy packages, so that they can be installed, on lunar systems.
sudo add-apt-repository -y -s deb https://security.ubuntu.com/ubuntu jammy main universeMake the directory if it doesn't exist yet. This location is recommended by the distribution maintainers.
sudo mkdir --parents --mode=0755 /etc/apt/keyringsDownload the key, convert the signing-key to a full Keyring required by apt and store in the keyring directory
wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | \
gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/nullamdgpu repository for jammy
echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu jammy main' \
| sudo tee /etc/apt/sources.list.d/amdgpu.list
sudo apt update -y AMDGPU DKMS
sudo apt install -y amdgpu-dkmsNote : This commonly produces warning message about 'Possible missing firmware' these are just wanrings and things work anyway, they can be ignored.
https://rocmdocs.amd.com/en/latest/deploy/linux/os-native/install.html
#echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/5.7.3 jammy main" \
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/5.7.3 jammy main" \
| sudo tee --append /etc/apt/sources.list.d/rocm.list
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' \
| sudo tee /etc/apt/preferences.d/rocm-pin-600
sudo apt update -yThis is lots of stuff, but comparatively small so worth including, as some stuff later may want as dependencies without much notice.
# ROCm...
sudo apt install -y rocm-dev rocm-libs rocm-hip-sdk rocm-dkms rocm-libs# ld.so.conf update
sudo tee --append /etc/ld.so.conf.d/rocm.conf <<EOF
/opt/rocm/lib
/opt/rocm/lib64
EOF
sudo ldconfig# update path
echo "PATH=/opt/rocm/bin:/opt/rocm/opencl/bin:$PATH" >> ~/.profilesudo /opt/rocm/bin/rocminfo | grep gfxFound : gfx1030 [ Radeon 6900 ] Found : gfx1100 [ Radeon 7900 ]
Of course note to change the user name to match your user.
sudo adduser `whoami` video
sudo adduser `whoami` render# git and git-lfs (large file support
sudo apt install -y git git-lfs
# development tool may be required later...
sudo apt install -y libstdc++-12-dev
# stable diffusion likes TCMalloc...
sudo apt install -y libtcmalloc-minimal4This section is optional, and as such has been moved to performance-tuning
nvtop Note : I have had issues with the distro version crashes with 2 GPUs, installing new version from sources works fine. Instructions for that are included at the bottom, as they depend on things installed between here and there. Project website : https://github.com/Syllo/nvtop
sudo apt install -y nvtop sudo apt install -y radeontop rovclocksudo rebootThis system is built to use its own venv ( rather than Conda )...
https://github.com/AUTOMATIC1111/stable-diffusion-webui Get the files...
cd
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
cd stable-diffusion-webuisudo apt install -y wget git python3.11 python3.11-venv libgl1 libglib2.0-0
python3.11 -m venv venv
source venv/bin/activate
python3.11 -m pip install -U pip
deactivatetee --append webui-user.sh <<EOF
# specify compatible python version
python_cmd="python3.11"
## Torch for ROCm
# generic import...
# export TORCH_COMMAND="pip install torch torchvision --index-url https://download.pytorch.org/whl/nightly/rocm5.7"
# use specific versions to avoid downloading all the nightlies... ( update dates as needed )
export TORCH_COMMAND="pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/rocm5.7"
## And if you want to call this from other programs...
export COMMANDLINE_ARGS="--api"
## crashes with 2 cards, so to get it to run on the second card (only), unremark the following
# export CUDA_VISIBLE_DEVICES="1"
EOFIf you don't do this, it will install a default to get you going. Note that these start files do include things that it needs you'll want to copy into the folder where you have other models ( to avoid issues )
#mv models models.1
#ln -s /path/to/models models Note that the first time it starts it may take it a while to go and get things it's not always good about saying what it's up to.
./webui.sh - variation of https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/scripts/install-comfyui-venv-linux.sh Includes ComfyUI-Manager
Same install of packages here as for Stable Diffusion ( included here in case you're not installed SD and just want ComfyUI... )
sudo apt install -y wget git python3 python3-venv libgl1 libglib2.0-0cd
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI/custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager
cd ..
python3 -m venv venv
source venv/bin/activate
# pre-install torch and torchvision from nightlies - note you may want to update versions...
python3 -m pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/rocm5.7
python3 -m pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/rocm5.7
python3 -m pip install -r custom_nodes/ComfyUI-Manager/requirements.txt --extra-index-url https://download.pytorch.org/whl/rocm5.7
# end vend if needed...
deactivateScripts for running the program...
# run_gpu.sh
tee --append run_gpu.sh <<EOF
#!/bin/bash
source venv/bin/activate
python3 main.py --preview-method auto
EOF
chmod +x run_gpu.sh
#run_cpu.sh
tee --append run_cpu.sh <<EOF
#!/bin/bash
source venv/bin/activate
python3 main.py --preview-method auto --cpu
EOF
chmod +x run_cpu.shUpdate the config file to point to Stable Diffusion (presuming it's installed...)
# config file - connecto stable-diffusion-webui
cp extra_model_paths.yaml.example extra_model_paths.yaml
sed -i "s@path/to@`echo ~`@g" extra_model_paths.yaml
# edit config file to point to your checkpoints etc
#vi extra_model_paths.yamlProject Website : https://github.com/oobabooga/text-generation-webui.git
First we'll need Conda ... Required for pytorch... Conda provides virtual environments for python, so that programs with different dependencies can have different environments. Here is more info on managing conda : https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html# Other notes : https://docs.conda.io/projects/conda/en/latest/user-guide/install/linux.html Download info : https://www.anaconda.com/download/
Anaconda ( if you prefer this to miniconda below )
#cd ~/Downloads/
#wget https://repo.anaconda.com/archive/Anaconda3-2023.09-0-Linux-x86_64.sh
#bash Anaconda3-2023.09-0-Linux-x86_64.sh -b
#cd ~
#ln -s anaconda3 condaMiniconda ( if you prefer this to Anaconda above... ) [ https://docs.conda.io/projects/miniconda/en/latest/ ]
cd ~/Downloads/
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh -b
cd ~
ln -s miniconda3 condaecho "PATH=~/conda/bin:$PATH" >> ~/.profile
source ~/.profile
conda update -y -n base -c defaults condaconda install -y cmake ninjaconda init
source ~/.profilesudo apt install -y pip
pip3 install --upgrade pip## show outdated packages...
#pip list --outdated
## check dependencies
#pip check
## install specified bersion
#pip install <packagename>==<version>conda create -n textgen python=3.11 -y
conda activate textgen# pre-install
pip install --pre cmake colorama filelock lit numpy Pillow Jinja2 \
mpmath fsspec MarkupSafe certifi filelock networkx \
sympy packaging requests \
--index-url https://download.pytorch.org/whl/rocm5.7pip install --pre torch torchvision torchtext torchaudio triton pytorch-triton-rocm \
--index-url https://download.pytorch.org/whl/rocm5.72024-04-24 - AMD's own ROCm version of bitsandbytes has been updated! - https://github.com/ROCm/bitsandbytes ( ver 0.44.0.dev0 at time of writing )
cd
git clone https://github.com/ROCm/bitsandbytes.git
cd bitsandbytes
pip install .cd
git clone https://github.com/oobabooga/text-generation-webui
cd text-generation-webuiThe default bitsandbytes for AMD is out of date and doesn't support GPU. So we installed one earlier ( may be unsupported... ) we'll run sed first to adjust that line of the requirements...
sed -i "s@bitsandbytes==@bitsandbytes>=@g" requirements_amd.txt
pip install -r requirements_amd.txt Exllama and Exllamav2 loaders ...
It appears ExLlama isn't being maintained and the emphasis is now on ExLlamav2... v2 has been updated to support Mixture of Experts (MoE such as Mixtral ).
2023-12-23 - After many tests, it appears that the exllamav2 that's installed above gives an error, so we're compiling and reinstalling exllama here as when we do that it does work.
2024-01-18 - Something has broken and exllamav2 won't compile so I've added a line to reset the checkout to the last known good / compiling version 0.0.11
2024-01-20 - Thanks to TurboDerp for resolving issue with exllamav2 so it plays nice with HIP. Remarked out workaround, in case such is useful in future.
# install exllama
#git clone https://github.com/turboderp/exllama repositories/exllama
# install exllamav2
git clone https://github.com/turboderp/exllamav2 repositories/exllamav2
cd repositories/exllamav2
# Force collection back to base 0.0.11
# git reset --hard a4ecea6
pip install . --index-url https://download.pytorch.org/whl/rocm5.7
cd ../..Models : If you're new to this - new models can be downloaded from the shell via a python script, or from a form in the interface. There are lots of them - https://huggingface.co Generally the GPTQ models by TheBloke are likely to load... https://huggingface.co/TheBloke The 30B/33B models will load on 24GB of VRAM, but may error, or run out of memory depending on usage and parameters. Worthy of mention, TurboDerp ( author of the exllama loaders ) has been posting exllamav2 ( exl2 ) processed versions of models - https://huggingface.co/turboderp ( for use with exllamav2 loader ) - when downloading, note the --branch option.
To get new models note the ~/text-generation-webui directory has a program " download-model.py " that is made for downloading models from HuggingFace's collection.
If you have old models, link pre-stored models into the models
# cd ~/text-generation-webui
# mv models models.1
# ln -s /path/to/models modelsLet's create a script (run.sh) to run the program...
tee --append run.sh <<EOF
#!/bin/bash
## activate conda
conda activate textgen
## command to run server...
python server.py --extensions sd_api_pictures send_pictures gallery
# if you want the server to listen on the local network so other machines can access it, add --listen.
#python server.py --listen --extensions sd_api_pictures send_pictures gallery
conda deactivate
EOF
chmod u+x run.shNote that to run the script :
source run.sh( As one from packages crashes on 2 GPUs, while this never version from sources works fine. ) project website : https://github.com/Syllo/nvtop optional - tool for displaying gpu / memory usage info The package for this crashes with 2 gpu's, here it is from source.
sudo apt install -y libdrm-dev libsystemd-dev libudev-dev
cd
git clone https://github.com/Syllo/nvtop.git
mkdir -p nvtop/build && cd nvtop/build
cmake .. -DNVIDIA_SUPPORT=OFF -DAMDGPU_SUPPORT=ON -DINTEL_SUPPORT=OFF
make
sudo make install