nvidia/tensorrt

1

trt-cpp-runtime-quickstart Load and run a TensorRT engine (.plan / .engine) from C++ using the TensorRT 11 / 10.x **modern Runtime API**, avoidi…

nvidia/tensorrt

5

2

trt-onnx-quickstart Build and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against O…

nvidia/tensorrt

5

3

trt-perf-analysis Validate and analyze TensorRT performance data from paired layer-info JSON and profile/latency JSON files.

nvidia/tensorrt

5

4

trt-strong-typing-migration Migrate a TensorRT build from weak typing (deprecated 10.12, removed 11.0) to strong typing — across Python INetworkD…

nvidia/tensorrt

4

5

trt-torch-quickstart Compile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default. U…

nvidia/tensorrt

4