Cutlery/immich
1
0
Fork 1
mirror of https://github.com/immich-app/immich.git synced 2025-06-23 15:30:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

DOCS

Browse Source
This commit is contained in:
yoni13 2025-01-13 00:44:22 +08:00
parent e6ff21b345
commit c109e28686
2 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/docs/features/ml-hardware-acceleration.md
View File

@ -10,6 +10,7 @@ You do not need to redo any machine learning jobs after enabling hardware accele
## Supported Backends
- ARM NN (Mali)
- RKNN (Rockchip)
- CUDA (NVIDIA GPUs with [compute capability](https://developer.nvidia.com/cuda-gpus) 5.2 or higher)
- OpenVINO (Intel discrete GPUs such as Iris Xe and Arc)
@ -34,6 +35,15 @@ You do not need to redo any machine learning jobs after enabling hardware accele
- The `hwaccel.ml.yml` file assumes an additional file `/lib/firmware/mali_csffw.bin`, so update accordingly if your device's driver does not require this file
- Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for ARM NN specific settings
#### RKNN
- You must have a supported Rockchip SoC, only RK3566 and RK3588 are supported at this moment.
- Make sure you have the appropriate linux kernel driver installed
- This is usually pre-installed on the device vendor's Linux images
- RKNPU driver V0.9.8 or later must be available in the host server
- You may confirm this by running `cat /sys/kernel/debug/rknpu/version` to check the version
- Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for RKNN specific settings
#### CUDA
- The GPU must have compute capability 5.2 or greater.

4
docs/docs/install/environment-variables.md
View File

@ -166,6 +166,10 @@ Redis (Sentinel) URL example JSON before encoding:
| `MACHINE_LEARNING_ANN_TUNING_LEVEL` | ARM-NN GPU tuning level (1: rapid, 2: normal, 3: exhaustive) | `2` | machine learning |
| `MACHINE_LEARNING_DEVICE_IDS`<sup>\*4</sup> | Device IDs to use in multi-GPU environments | `0` | machine learning |
| `MACHINE_LEARNING_MAX_BATCH_SIZE__FACIAL_RECOGNITION` | Set the maximum number of faces that will be processed at once by the facial recognition model | None (`1` if using OpenVINO) | machine learning |
| `MACHINE_LEARNING_RKNN` | Enable RKNN hardware acceleration if supported | `True` | machine learning |
| `MACHINE_LEARNING_RKNN_TEXTUAL_THREADS` | How many threads of RKNN runtime should be spinned up while infrencing textual model. | 1 | machine learning |
| `MACHINE_LEARNING_RKNN_VISUAL_THREADS` | How many threads of RKNN runtime should be spinned up while infrencing visual model. | 1 | machine learning |
| `MACHINE_LEARNING_RKNN_TEXTUAL_THREADS` | How many threads of RKNN runtime should be spinned up while infrencing textual model. | 1 | machine learning || `MACHINE_LEARNING_RKNN_FACIAL_THREADS` | How many threads of RKNN runtime should be spinned up while infrencing facial model. | 1 | machine learning |
\*1: It is recommended to begin with this parameter when changing the concurrency levels of the machine learning service and then tune the other ones.