16
[Feature] Apple Container and CoreML Support for Machine Learning
Source: immich-app/immich#25726 · opened by @burnziii
I have searched the existing feature requests, both open and closed, to make sure this is not a duplicate request. • Yes The feature Currently, Immich's machine learning features rely on ONNX Runtime or OpenVINO, which work well on x86 systems with NVIDIA GPUs or Intel hardware. However, for users running Immich on Apple Silicon Macs (M1/M2/M3/M4), the ML workloads cannot leverage the dedicated Neural Engine, resulting in suboptimal performance and higher power consumption compared to native CoreML execution. Additionally, with Apple introducing container support for macOS, there's an opportunity to provide a more native deployment experience for Mac users. …
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature] Separate Image Preview for Machine Learning
1 vote · 0 comments
Improve machine learning resilience in low VRAM scenarios (CUDA)
1 vote · 0 comments
[Feature] Support for arm64 for CUDA (immich-machine-learning)
41 votes · 0 comments
[Feature] DirectML execution provider for Machine Learning (AMD GPU Support on Windows/WSL2)
8 votes · 0 comments
[Feature] Automatically pause and resume Remote Machine Learning for on-and-off beefy machine
18 votes · 0 comments
No comments yet.