Worker (pid:36955) was sent code 139! when using machine learning with ROCm
I'm trying to use machine learning with ROCm. I'm using a Hawk Point GPU. In order for it to work I have HSA_OVERRIDE_GFX_VERSION=10.3.0
Here's the section for my docker-compose.yml
Here's the section for my docker-compose.yml
immich-machine-learning:
container_name: immich_machine_learning
# For hardware acceleration, add one of -[armnn, cuda, rocm, openvino, rknn] to the image tag.
# Example tag: ${IMMICH_VERSION:-release}-cuda
image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-rocm
extends: # uncomment this section for hardware acceleration - see https://docs.immich.app/features/ml-hardware-acceleration
file: hwaccel.ml.yml
service: rocm # set to one of [armnn, cuda, rocm, openvino, openvino-wsl, rknn] for accelerated inference - use the `-wsl` version for WSL2 where applicable
volumes:
- /cache/immich:/cache
- /var/run/postgresql:/var/run/postgresql
- /var/run/valkey:/var/run/valkey
env_file:
- .env
restart: always
healthcheck:
disable: false immich-machine-learning:
container_name: immich_machine_learning
# For hardware acceleration, add one of -[armnn, cuda, rocm, openvino, rknn] to the image tag.
# Example tag: ${IMMICH_VERSION:-release}-cuda
image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-rocm
extends: # uncomment this section for hardware acceleration - see https://docs.immich.app/features/ml-hardware-acceleration
file: hwaccel.ml.yml
service: rocm # set to one of [armnn, cuda, rocm, openvino, openvino-wsl, rknn] for accelerated inference - use the `-wsl` version for WSL2 where applicable
volumes:
- /cache/immich:/cache
- /var/run/postgresql:/var/run/postgresql
- /var/run/valkey:/var/run/valkey
env_file:
- .env
restart: always
healthcheck:
disable: false