Nvidia's TensorRT Model Connect turns checkpoints into C++ inference

Nvidia released TensorRT Model Connect (TRTMC) in public preview, an Apache-2.0 tool that converts a Hugging Face or local model checkpoint directly into native C++ inference in two commands, with no intermediate ONNX export step. It ships a July 29, 2026 GB300 snapshot covering 105 release profiles across 76 model families.

Why it matters: By collapsing the checkpoint-to-deployment pipeline, Nvidia lowers the barrier to running models in production without PyTorch in the runtime path, reinforcing its grip on the inference software stack even as rivals like AMD push into AI chip design.