FiRddlmZddlmZddlZddlmZddlmZGddeZ y) ) annotations)PathN)check_requirements) BaseBackendc eZdZdZddZddZy) TritonBackendzNVIDIA Triton Inference Server backend for remote model serving. Connects to and runs inference with models hosted on an NVIDIA Triton Inference Server instance via HTTP or gRPC protocols. The model is specified using a triton:// URL scheme. ctdddlm}|||_t |jdr&|j |jj yy)zConnect to a remote model on an NVIDIA Triton Inference Server. Args: weight (str | Path): Triton model URL (e.g., 'http://localhost:8000/model_name'). ztritonclient[all]r)TritonRemoteModelmetadataN)rultralytics.utils.tritonr modelhasattrapply_metadatar )selfweightr s `/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/ultralytics/nn/backends/triton.py load_modelzTritonBackend.load_modelsI ./>&v.  4::z *    3 3 4 +c\|j|jjS)aRun inference via the NVIDIA Triton Inference Server. Args: im (torch.Tensor): Input image tensor in BCHW format, normalized to [0, 1]. Returns: (list): Model predictions as a list of numpy arrays from the Triton server. )rcpunumpy)rims rforwardzTritonBackend.forward$s zz"&&(..*++rN)rz str | PathreturnNone)rz torch.Tensorrlist)__name__ __module__ __qualname____doc__rrrrr r s 5 ,rr ) __future__rpathlibrtorchultralytics.utils.checksrbaserr r"rrr(s"# 7,K,r