Erich Blume 870d602019 Use Frigate default model instead of custom YOLOv9m ... The YOLOv9m ONNX model has ops not fully partitionable to CUDA EP, causing CUDA graph capture to fail on the -tensorrt image. Use the default model that ships with the image and is tested for GPU inference. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-19 13:28:35 -08:00
..
apps	Port Frigate NVR to ringtail k3s with GPU acceleration	2026-02-19 11:41:47 -08:00
manifests	Use Frigate default model instead of custom YOLOv9m	2026-02-19 13:28:35 -08:00