blakeblackshear.frigate/frigate/embeddings/onnx
Nicolas Mowen 81d7c47129
Optimize OpenVINO and ONNX Model Runners (#20063)
* Use re-usable inference request to reduce CPU usage

* Share tensor

* Don't count performance

* Create openvino runner class

* Break apart onnx runner

* Add specific note about inability to use CUDA graphs for some models

* Adjust rknn to use RKNNRunner

* Use optimized runner

* Add support for non-complex models for CudaExecutionProvider

* Use core mask for rknn

* Correctly handle cuda input

* Cleanup

* Sort imports
2025-09-14 06:22:22 -06:00
..
base_embedding.py Fix various typing issues (#18187) 2025-05-13 08:27:20 -06:00
face_embedding.py Optimize OpenVINO and ONNX Model Runners (#20063) 2025-09-14 06:22:22 -06:00
jina_v1_embedding.py Optimize OpenVINO and ONNX Model Runners (#20063) 2025-09-14 06:22:22 -06:00
jina_v2_embedding.py Optimize OpenVINO and ONNX Model Runners (#20063) 2025-09-14 06:22:22 -06:00
lpr_embedding.py Optimize OpenVINO and ONNX Model Runners (#20063) 2025-09-14 06:22:22 -06:00