AMD GPU ROCm - Revision history

Joachim: /* Todo */

2025-10-12T18:34:55Z

Todo

← Older revision		Revision as of 18:34, 12 October 2025
Line 107:		Line 107:
	zypper info rocm: Version : 6.4.3-2.2		zypper info rocm: Version : 6.4.3-2.2

	~~probably need~~ to ~~adapt image to downgrade from rocm7 to rocm6~~.4.3		Found out whisper uses onnxruntime. There are AMD provided docker images with that runtime but ist still didn't work.
			Now the error is CUDA version mismatch between driver and runtime. Tried several combinations. No luck.
			Switching to Nvidia... :(

	= Configure Home Assistant =		= Configure Home Assistant =

Joachim: /* Todo */

2025-10-08T17:02:07Z

Todo

← Older revision		Revision as of 17:02, 8 October 2025
Line 102:		Line 102:
	It creates an own .venv, but installing torch there with above pip does not help		It creates an own .venv, but installing torch there with above pip does not help

			with docker approach:
	whisper at start: RuntimeError: CUDA failed with error no CUDA-capable device is detected		whisper at start: RuntimeError: CUDA failed with error no CUDA-capable device is detected

			zypper info rocm: Version : 6.4.3-2.2

			probably need to adapt image to downgrade from rocm7 to rocm6.4.3

	= Configure Home Assistant =		= Configure Home Assistant =

Joachim: /* Wyoming Piper */

2025-10-08T16:58:36Z

Wyoming Piper

@@ Line 64: / Line 64: @@
   curl -L -s "https://github.com/rhasspy/piper/releases/download/v1.2.0/piper_amd64.tar.gz" | tar -zxvf - -C ..
   HF_HUB_CACHE=../wyoming-piper-data PATH="../piper:$PATH" script/run --voice de_DE-thorsten-high --uri 'tcp://0.0.0.0:10200' --data-dir ../wyoming-piper-data --download-dir ../wyoming-piper-data --use-cuda
 = Todo =

Joachim: /* Install rocm meta package */

2025-10-08T02:23:17Z

Install rocm meta package

← Older revision		Revision as of 02:23, 8 October 2025
Line 6:		Line 6:
	sudo zypper ref		sudo zypper ref
	sudo zypper in rocm		sudo zypper in rocm
	sudo usermod -aG render # restart session		sudo usermod -aG render,video # restart session

	= Test Installation =		= Test Installation =

Joachim: /* Wyoming Piper */

2025-10-08T02:00:56Z

Wyoming Piper

← Older revision		Revision as of 02:00, 8 October 2025
Line 63:		Line 63:
	script/setup		script/setup
	curl -L -s "https://github.com/rhasspy/piper/releases/download/v1.2.0/piper_amd64.tar.gz" \| tar -zxvf - -C ..		curl -L -s "https://github.com/rhasspy/piper/releases/download/v1.2.0/piper_amd64.tar.gz" \| tar -zxvf - -C ..
	HF_HUB_CACHE=../wyoming-piper-data PATH="../piper:$PATH" script/run --voice de_DE-thorsten-high --uri 'tcp://0.0.0.0:10200' --data-dir ../wyoming-piper-data --download-dir ../wyoming-piper-data		HF_HUB_CACHE=../wyoming-piper-data PATH="../piper:$PATH" script/run --voice de_DE-thorsten-high --uri 'tcp://0.0.0.0:10200' --data-dir ../wyoming-piper-data --download-dir ../wyoming-piper-data --use-cuda

	= Todo =		= Todo =

Joachim: /* Todo */

2025-10-08T02:00:19Z

Todo

← Older revision		Revision as of 02:00, 8 October 2025
Line 66:		Line 66:

	= Todo =		= Todo =
	For now, I tried to use --device cuda (whisper~~) and --use-cuda (piper)~~ and failed.
	~~Both create their~~ own .venv, but installing torch there with above pip does not help		For now, I tried to use --device cuda with whisper and failed.
			It creates an own .venv, but installing torch there with above pip does not help

			whisper at start: RuntimeError: CUDA failed with error no CUDA-capable device is detected

	= Configure Home Assistant =		= Configure Home Assistant =

Joachim: /* PyTorch */

2025-10-08T01:49:22Z

PyTorch

← Older revision		Revision as of 01:49, 8 October 2025
Line 43:		Line 43:

	python -c 'import torch; print(torch.cuda.is_available())'		python -c 'import torch; print(torch.cuda.is_available())'

			= Wyoming Faster Whisper =

			running a server for Home Assistant voice commands

			mkdir wyoming-faster-whisper-data
			git clone https://github.com/rhasspy/wyoming-faster-whisper.git
			cd wyoming-faster-whisper
			script/setup
			HF_HUB_CACHE=../wyoming-faster-whisper-data script/run --device cpu --model large-v3 --language de --uri 'tcp://0.0.0.0:10300' --data-dir ../wyoming-faster-whisper-data --download-dir ../wyoming-faster-whisper-data

			= Wyoming Piper =

			see https://github.com/rhasspy/wyoming-piper?tab=readme-ov-file#local-install

			mkdir wyoming-piper-data
			git clone https://github.com/rhasspy/wyoming-piper.git
			cd wyoming-piper
			script/setup
			curl -L -s "https://github.com/rhasspy/piper/releases/download/v1.2.0/piper_amd64.tar.gz" \| tar -zxvf - -C ..
			HF_HUB_CACHE=../wyoming-piper-data PATH="../piper:$PATH" script/run --voice de_DE-thorsten-high --uri 'tcp://0.0.0.0:10200' --data-dir ../wyoming-piper-data --download-dir ../wyoming-piper-data

			= Todo =
			For now, I tried to use --device cuda (whisper) and --use-cuda (piper) and failed.
			Both create their own .venv, but installing torch there with above pip does not help

			= Configure Home Assistant =

			Settings/Integrations/Wyoming Protocol: Add Service (host and port as used above, type is autodetected)
			Settings/Voice Assistants: Add Assistant: some name, STT->faster-whisper, TTS->piper

Joachim: /* AMD GPU ROCm */

2025-10-07T23:37:06Z

AMD GPU ROCm

← Older revision		Revision as of 23:37, 7 October 2025
Line 1:		Line 1:
	~~= AMD GPU ROCm =~~

	how to use amd grafic cards for speeding up calculations un tumbleweed similar tu nvidia with cuda		how to use amd grafic cards for speeding up calculations un tumbleweed similar tu nvidia with cuda

	== Install rocm meta package		= Install rocm meta package =

	sudo zypper ar https://download.opensuse.org/repositories/science:/GPU:/ROCm:/Work/openSUSE_Tumbleweed/ science_GPU_ROCm		sudo zypper ar https://download.opensuse.org/repositories/science:/GPU:/ROCm:/Work/openSUSE_Tumbleweed/ science_GPU_ROCm
Line 10:		Line 8:
	sudo usermod -aG render # restart session		sudo usermod -aG render # restart session

	== Test Installation ==		= Test Installation =

	clinfo -l		clinfo -l
Line 31:		Line 29:
	Name: amdgcn-amd-amdhsa--gfx10-3-generic		Name: amdgcn-amd-amdhsa--gfx10-3-generic

	== PyTorch ==		= PyTorch =

	for python projects like wyoming using pytorch add rocm support to a virtual environment.		for python projects like wyoming using pytorch add rocm support to a virtual environment.

Joachim: Created page with "= AMD GPU ROCm = how to use amd grafic cards for speeding up calculations un tumbleweed similar tu nvidia with cuda == Install rocm meta package sudo zypper ar https://download.opensuse.org/repositories/science:/GPU:/ROCm:/Work/openSUSE_Tumbleweed/ science_GPU_ROCm sudo zypper ref sudo zypper in rocm sudo usermod -aG render # restart session == Test Installation == clinfo -l Should output something like this: Platform #0: AMD Accelerated Parallel Processing..."

2025-10-07T23:36:24Z

Created page with "= AMD GPU ROCm = how to use amd grafic cards for speeding up calculations un tumbleweed similar tu nvidia with cuda == Install rocm meta package sudo zypper ar https://download.opensuse.org/repositories/science:/GPU:/ROCm:/Work/openSUSE_Tumbleweed/ science_GPU_ROCm sudo zypper ref sudo zypper in rocm sudo usermod -aG render # restart session == Test Installation == clinfo -l Should output something like this: Platform #0: AMD Accelerated Parallel Processing..."

New page

= AMD GPU ROCm =

how to use amd grafic cards for speeding up calculations un tumbleweed similar tu nvidia with cuda

== Install rocm meta package

sudo zypper ar https://download.opensuse.org/repositories/science:/GPU:/ROCm:/Work/openSUSE_Tumbleweed/ science_GPU_ROCm
sudo zypper ref
sudo zypper in rocm
sudo usermod -aG render # restart session

== Test Installation ==

clinfo -l

Should output something like this:

Platform #0: AMD Accelerated Parallel Processing
+-- Device #0: gfx1201
`-- Device #1: gfx1036

rocminfo | grep gfx

Should output something like

Name: gfx1201
Name: amdgcn-amd-amdhsa--gfx1201
Name: amdgcn-amd-amdhsa--gfx12-generic
Name: gfx1036
Name: amdgcn-amd-amdhsa--gfx1036
Name: amdgcn-amd-amdhsa--gfx10-3-generic

== PyTorch ==

for python projects like wyoming using pytorch add rocm support to a virtual environment.
See https://pytorch.org/get-started/locally/ for the current final pip command

cd your/venv/basedirectory
python3 -m venv wyoming
. wyoming/bin/activate
pip install --upgrade pip
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4

Test with (should print True)

python -c 'import torch; print(torch.cuda.is_available())'