41
[Feature] Support for arm64 for CUDA (immich-machine-learning)
Source: immich-app/immich#10647 · opened by @gowthamravichandran
I have searched the existing feature requests to make sure this is not a duplicate request.
• Yes
The feature
Docker Image for immich-machine-learning-cuda does not support arm64 processors at the moment.
Get the following message when trying to pull ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-cuda
no matching manifest for linux/arm64/v8 in the manifest list entries
Running immich in arm64 processor with cuda enabled gpus like Nvidia Jetson devices isnt possible and is currently forced to use the cpu instead of gpu.
Can we support a docker image for cuda enabled arm64 processors?
Platform
• Server
• Web
• Mobile
• Yes
The feature
Docker Image for immich-machine-learning-cuda does not support arm64 processors at the moment.
Get the following message when trying to pull ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-cuda
no matching manifest for linux/arm64/v8 in the manifest list entries
Running immich in arm64 processor with cuda enabled gpus like Nvidia Jetson devices isnt possible and is currently forced to use the cpu instead of gpu.
Can we support a docker image for cuda enabled arm64 processors?
Platform
• Server
• Web
• Mobile
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature] Upgrade to ONNX Runtime 1.27.0 for official CUDA 13 support
1 vote · 0 comments
[Feature] DirectML execution provider for Machine Learning (AMD GPU Support on Windows/WSL2)
8 votes · 0 comments
Improve machine learning resilience in low VRAM scenarios (CUDA)
1 vote · 0 comments
[Feature] JPEG-XL Support
62 votes · 0 comments
[Feature] Add JPEG XR (JXR) support, including HDR/scRGB
3 votes · 0 comments
No comments yet.