I was troubleshooting low FPS in a TensorRT-based RTSP video analytics pipeline on a customer's server. The input was a 1920×1080 stream at 25 FPS, running on an NVIDIA GeForce RTX 5070 Ti. The pose model already used TensorRT, but the application was processing only 8–10 FPS .

Inference was accelerated. The video pipeline wasn't.

After changing how frames moved through the application, I measured 24.64 processed FPS against the same 25 FPS source. That measurement was taken before the OCR queue ; it was not a benchmark of end-to-end OCR or video delivery latency.

I didn't replace the pose model. I changed the data path around it.

Why My RTSP + TensorRT Pipeline Was Stuck at 8–10 FPS

The application did more than pose detection.…