administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-09-27 09:38:59 +03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Apple Silicon Macs via lighter: ONNX detector on the Neural Engine and media engine decode (#24453)

Browse Source 
* Run ONNX models on a Mac's Neural Engine through lighter's plugin provider

lighter's lighter.sh/ane device places an ONNX Runtime plugin execution
provider in the container. When it is present, the ONNX session setup
registers it once and opens sessions on its Neural Engine device, the same
place CUDA, ROCm and OpenVINO are chosen, so the onnx detector (and any
model that is not pinned to the CPU) runs there with no configuration. The
hardware probe reports it as an onnx unit.

* docs: hardware decode on an Apple Silicon Mac under lighter

A community section on the video decoding page: lighter's lighter.sh/video
device, hwaccel_args -c:v h264_v4l2m2m, and why the Raspberry Pi presets
decode a single-stream camera in software. The detector docs link to it.

* docs: set the lighter decoder per camera when codecs are mixed

* docs: the ONNX detector on a Mac's Neural Engine under lighter

* Format the Neural Engine provider setup

* Fall back to the default providers when the Neural Engine cannot load a model

* Apple Silicon ffmpeg presets for lighter's media engine, recommended when it is present
This commit is contained in:
Nick Rogers
2026-09-24 15:37:32 -06:00
committed by GitHub
parent c5889ef35f
commit c959df32c9
16 changed files with 413 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/configuration/ffmpeg_presets.md
+13 -11
View File
@@ -17,17 +17,19 @@ Hardware acceleration arguments tell FFmpeg to decode your camera's video stream
See [the hardware acceleration docs](/configuration/hardware_acceleration_video.md) for details on setting up hardware acceleration for your GPU / iGPU, then select the preset that matches your hardware.
| Preset (YAML config) | UI Label | Usage | Notes |
| --------------------- | ----------------------- | --------------------------------- | --------------------------------------------------------------- |
| preset-rpi-64-h264 | Raspberry Pi (H.264) | 64-bit Raspberry Pi, H.264 stream | |
| preset-rpi-64-h265 | Raspberry Pi (H.265) | 64-bit Raspberry Pi, H.265 stream | |
| preset-vaapi | VAAPI (Intel/AMD GPU) | Intel or AMD GPU via VAAPI | Check the hwaccel docs to ensure the correct driver is selected |
| preset-intel-qsv-h264 | Intel QuickSync (H.264) | Intel QuickSync, H.264 stream | If you have issues, use the VAAPI preset instead |
| preset-intel-qsv-h265 | Intel QuickSync (H.265) | Intel QuickSync, H.265 stream | If you have issues, use the VAAPI preset instead |
| preset-nvidia | NVIDIA GPU | NVIDIA GPU | |
| preset-jetson-h264 | NVIDIA Jetson (H.264) | NVIDIA Jetson, H.264 stream | |
| preset-jetson-h265 | NVIDIA Jetson (H.265) | NVIDIA Jetson, H.265 stream | |
| preset-rkmpp | Rockchip RKMPP | Rockchip MPP | Use an image with the `-rk` suffix and run in privileged mode |
| Preset (YAML config) | UI Label | Usage | Notes |
| ------------------------- | ----------------------- | --------------------------------------------- | --------------------------------------------------------------- |
| preset-rpi-64-h264 | Raspberry Pi (H.264) | 64-bit Raspberry Pi, H.264 stream | |
| preset-rpi-64-h265 | Raspberry Pi (H.265) | 64-bit Raspberry Pi, H.265 stream | |
| preset-apple-silicon-h264 | Apple Silicon (H.264) | Apple Silicon Mac under lighter, H.264 stream | Needs the `lighter.sh/video` device |
| preset-apple-silicon-h265 | Apple Silicon (H.265) | Apple Silicon Mac under lighter, H.265 stream | Needs the `lighter.sh/video` device |
| preset-vaapi | VAAPI (Intel/AMD GPU) | Intel or AMD GPU via VAAPI | Check the hwaccel docs to ensure the correct driver is selected |
| preset-intel-qsv-h264 | Intel QuickSync (H.264) | Intel QuickSync, H.264 stream | If you have issues, use the VAAPI preset instead |
| preset-intel-qsv-h265 | Intel QuickSync (H.265) | Intel QuickSync, H.265 stream | If you have issues, use the VAAPI preset instead |
| preset-nvidia | NVIDIA GPU | NVIDIA GPU | |
| preset-jetson-h264 | NVIDIA Jetson (H.264) | NVIDIA Jetson, H.264 stream | |
| preset-jetson-h265 | NVIDIA Jetson (H.265) | NVIDIA Jetson, H.265 stream | |
| preset-rkmpp | Rockchip RKMPP | Rockchip MPP | Use an image with the `-rk` suffix and run in privileged mode |
<ConfigTabs>
<TabItem value="ui">
docs/docs/configuration/hardware_acceleration_video.md
+36
View File
@@ -43,6 +43,10 @@ Frigate supports presets for optimal hardware accelerated video decoding:
- [RKNN](#rockchip-platform): Frigate can utilize the media engine in RockChip SOCs to accelerate video decoding.
**Apple Silicon Mac** <CommunityBadge />
- [lighter](#apple-silicon-mac-lighter): Frigate can utilize the media engine in Apple Silicon Macs to accelerate video decoding, when running under the lighter container runtime.
**Other Hardware**
Depending on your system, these presets may not be compatible, and you may need to use manual hwaccel args to take advantage of your hardware. More information on hardware accelerated decoding for ffmpeg can be found here: https://trac.ffmpeg.org/wiki/HWAccelIntro
@@ -533,3 +537,35 @@ output_args:
Make sure that your SoC supports hardware acceleration for your input stream and your input stream is h264 encoding. For example, if your camera streams with h264 encoding, your SoC must be able to de- and encode with it. If you are unsure whether your SoC meets the requirements, take a look at the datasheet.
:::
## Apple Silicon Mac (lighter)
[lighter](https://github.com/fieldwork-ai/lighter) is an open-source container runtime for macOS. It gives a container the Mac's media engine as a standard V4L2 decoder, backed by VideoToolbox, so Frigate decodes H.264 and H.265 streams in hardware with the ffmpeg it already ships. It works on M1 and newer Macs with lighter 0.9.2 or newer.
Give the container the video device. With Docker Compose:
```yaml {4-5}
services:
frigate:
...
devices:
- lighter.sh/video=all
```
Or with `docker run`, add `--device lighter.sh/video=all`.
Then set the preset for the codec your cameras stream. The decoder is specific to the codec, so if your cameras mix H.264 and H.265, set the preset for the most common codec globally and override it on the other cameras:
```yaml
ffmpeg:
hwaccel_args: preset-apple-silicon-h264
cameras:
garage: # an H.265 camera
ffmpeg:
hwaccel_args: preset-apple-silicon-h265
```
The presets decode on the media engine and encode the Birdseye restream and timelapses there too. Scaling to the detect resolution runs on the CPU, as ffmpeg's V4L2 decoders cannot scale.
lighter can also run object detection on the Mac's Neural Engine; see [Apple Neural Engine (lighter)](object_detectors.md#apple-neural-engine-lighter).
docs/docs/configuration/object_detectors.md
+21 -1
View File
@@ -34,6 +34,7 @@ Frigate supports multiple different detectors that work on different types of ha
**Apple Silicon**
- [Apple Silicon](#apple-silicon-detector): Apple Silicon can run on M1 and newer Apple Silicon devices.
- <CommunityBadge /> [ONNX](#apple-neural-engine-lighter): the ONNX detector runs on the Neural Engine of M1 and newer Macs when Frigate runs under the lighter container runtime.
**Intel**
@@ -484,7 +485,7 @@ See [ONNX supported models](#onnx) for supported models, there are some caveats:
## ONNX
ONNX is an open format for building machine learning models, Frigate supports running ONNX models on CPU, OpenVINO, ROCm, and TensorRT. On startup Frigate will automatically try to use a GPU if one is available.
ONNX is an open format for building machine learning models, Frigate supports running ONNX models on CPU, OpenVINO, ROCm, TensorRT, and a Mac's Neural Engine. On startup Frigate will automatically try to use a GPU if one is available.
:::info
@@ -500,6 +501,9 @@ If the correct build is used for your GPU then the GPU will be detected and used
- Nvidia GPUs will automatically be detected and used with the ONNX detector in the `-tensorrt` Frigate image.
- Jetson devices will automatically be detected and used with the ONNX detector in the `-tensorrt-jp6` Frigate image.
- **Apple Silicon Mac** <CommunityBadge />
- The Neural Engine will automatically be detected and used with the ONNX detector when Frigate runs under lighter with its Neural Engine device. See [Apple Neural Engine (lighter)](#apple-neural-engine-lighter).
:::
:::tip
@@ -515,6 +519,22 @@ models:
:::
### Apple Neural Engine (lighter) {#apple-neural-engine-lighter}
[lighter](https://github.com/fieldwork-ai/lighter) is an open-source container runtime for macOS. A container started with its `lighter.sh/ane` device gets an ONNX Runtime execution provider that runs models on the Mac's Neural Engine, and the ONNX detector uses it automatically, with the same models and configuration as on any other hardware. It works on M1 and newer Macs with lighter 0.9.2 or newer.
Give the Frigate container the Neural Engine device. With Docker Compose:
```yaml
services:
frigate:
image: ghcr.io/blakeblackshear/frigate:stable-standard-arm64
devices:
- lighter.sh/ane=all
```
Or with `docker run`, add `--device lighter.sh/ane=all`. Frigate then reports the Neural Engine under **Settings > System > Detection models**, and the ONNX detector's model loads on it. lighter can also decode camera streams on the Mac's media engine; see [Video Decoding](hardware_acceleration_video.md#apple-silicon-mac-lighter).
### Configuration {#configuration-onnx}
<ModelConfigDropdown detectorTitle="ONNX" models={objectDetectorsModels.onnx.models} />
docs/docs/frigate/hardware.md
+11 -1
View File
@@ -78,6 +78,10 @@ Frigate supports multiple different detectors that work on different types of ha
**Apple Silicon**
- [ONNX via lighter](#apple-silicon): The ONNX detector runs on the Neural Engine of M1 and newer Macs when Frigate runs in the lighter container runtime
- [Supports the same model architectures as the ONNX detector](../../configuration/object_detectors#apple-neural-engine-lighter)
- Runs inside the Frigate container, with no separate detector process to set up
- The recommended way to run Frigate on a Mac
- [Apple Silicon](#apple-silicon): Apple Silicon is usable on all M1 and newer Apple Silicon devices to provide efficient and fast object detection
- [Supports primarily ssdlite and mobilenet model architectures](../../configuration/object_detectors#apple-silicon-detector)
- Runs well with any size models including large
@@ -211,7 +215,13 @@ Inference is done with the `onnx` detector type. Speeds will vary greatly depend
### Apple Silicon
With the [Apple Silicon](../configuration/object_detectors.md#apple-silicon-detector) detector Frigate can take advantage of the NPU in M1 and newer Apple Silicon.
Frigate on a Mac is best run in the [lighter](https://github.com/fieldwork-ai/lighter) container runtime, where the [ONNX detector](../configuration/object_detectors.md#apple-neural-engine-lighter) runs on the Neural Engine of M1 and newer Macs from inside the Frigate container. There is no separate detector process to install or keep running, and the same container can decode video on the Mac's media engine.
| Name | YOLOv9 Inference Time | YOLO-NAS Inference Time | RF-DETR Inference Time |
| ---- | -------------------------------------- | ----------------------- | ---------------------- |
| M1 | t-320: 3.3 ms s-320: 7 ms s-640: 13 ms | 320: 6.6 ms | Nano-320: 38 ms |
Alternatively, with the [Apple Silicon](../configuration/object_detectors.md#apple-silicon-detector) detector Frigate can take advantage of the NPU in M1 and newer Apple Silicon.
:::warning