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

* 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

frigate/detectors/hardware.py

@@ -25,6 +25,7 @@ SYS_ROOT = "/sys"
 DEV_ROOT = "/dev"
 PROC_ROOT = "/proc"
 ETC_ROOT = "/etc"
+LIB_ROOT = "/usr/lib"
 
 # a Coral reports as Global Unichip until its firmware is loaded, then as Google
 CORAL_USB_IDS = {("1a6e", "089a"), ("18d1", "9302")}
@@ -317,6 +318,19 @@ def detect_synaptics() -> DetectionHardware | None:
     return _hardware("synaptics", "synaptics", "Synaptics NPU", units)
 
 
+def detect_lighter_ane() -> DetectionHardware | None:
+    """Find a Mac's Neural Engine by the provider library lighter's device places."""
+    library = os.environ.get(
+        "LIGHTER_ANE_EP", f"{LIB_ROOT}/lighter/liblighter_ane_ep.so"
+    )
+    if not os.path.exists(library):
+        return None
+
+    # runs through onnx, whose session picks lighter's provider when it is present
+    units = [HardwareUnit(device="onnx", label="Neural Engine")]
+    return _hardware("onnx:lighter", "onnx", "Apple Neural Engine", units)
+
+
 def detect_cpu() -> DetectionHardware:
     """The CPU, which is always available."""
     units = [HardwareUnit(device="cpu", label="CPU")]
@@ -338,6 +352,7 @@ PROBES = (
     detect_rockchip,
     detect_axengine,
     detect_synaptics,
+    detect_lighter_ane,
     detect_cpu,
 )