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

frigate/embeddings/onnx/jina_v1_embedding.py

@@ -12,11 +12,11 @@ from transformers.utils.logging import disable_progress_bar
 
 from frigate.comms.inter_process import InterProcessRequestor
 from frigate.const import MODEL_CACHE_DIR, UPDATE_MODEL_STATE
+from frigate.detectors.detection_runners import BaseModelRunner, get_optimized_runner
 from frigate.types import ModelStatusTypesEnum
 from frigate.util.downloader import ModelDownloader
 
 from .base_embedding import BaseEmbedding
-from .runner import ONNXModelRunner
 
 warnings.filterwarnings(
     "ignore",
@@ -125,7 +125,7 @@ class JinaV1TextEmbedding(BaseEmbedding):
                 clean_up_tokenization_spaces=True,
             )
 
-            self.runner = ONNXModelRunner(
+            self.runner = get_optimized_runner(
                 os.path.join(self.download_path, self.model_file),
                 self.device,
             )
@@ -170,7 +170,7 @@ class JinaV1ImageEmbedding(BaseEmbedding):
         self.device = device
         self.download_path = os.path.join(MODEL_CACHE_DIR, self.model_name)
         self.feature_extractor = None
-        self.runner: ONNXModelRunner | None = None
+        self.runner: BaseModelRunner | None = None
         files_names = list(self.download_urls.keys())
         if not all(
             os.path.exists(os.path.join(self.download_path, n)) for n in files_names
@@ -203,7 +203,7 @@ class JinaV1ImageEmbedding(BaseEmbedding):
                 f"{MODEL_CACHE_DIR}/{self.model_name}",
             )
 
-            self.runner = ONNXModelRunner(
+            self.runner = get_optimized_runner(
                 os.path.join(self.download_path, self.model_file),
                 self.device,
             )