YOLOv7 TensorRT Inference Engine
YOLOv7 inference pipeline in C++ and Python optimized for NVIDIA Jetson using TensorRT, with CUDA-accelerated pre and post processing and CMake build. Delivers real-time object detection on constrained edge hardware with FP16 and INT8 quantization paths.
Mutte Ur Rehman
Independent AI Engineer · LLMs, RAG, Agents · Computer Vision on Edge
I build production AI systems. LLM agents, RAG pipelines, and computer vision on the edge.