From ba4889879755dea49b1fb66806256860e5ec980a Mon Sep 17 00:00:00 2001 From: Srilekha Date: Sat, 22 Nov 2025 00:09:54 +0530 Subject: [PATCH] Add validation section for TensorRT models Added a section on validating TensorRT models before deployment, including an example command. --- docs/index.md | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/docs/index.md b/docs/index.md index 84f3438f98..158b66e253 100644 --- a/docs/index.md +++ b/docs/index.md @@ -118,4 +118,19 @@ Join the [Triton and TensorRT community](https://www.nvidia.com/en-us/deep-learn practices, and more. Need enterprise support? NVIDIA global support is available for Triton Inference Server with the [NVIDIA AI Enterprise software suite](https://www.nvidia.com/en-us/data-center/products/ai-enterprise/). -See the [Latest Release Notes](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/) for updates on the newest features and bug fixes. \ No newline at end of file +See the [Latest Release Notes](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/) for updates on the newest features and bug fixes. +## Validating a TensorRT Model Before Deployment + +Model Navigator provides a simple workflow for validating TensorRT `.plan` +models before packaging them into a Triton model repository. This helps ensure +that exported models load correctly, run with the expected shapes, and match +runtime requirements. + +Example: + +```bash +model-navigator validate \ + --model-path ./model.plan \ + --model-format tensorrt \ + --input-shapes "x:[1,3,224,224]" \ + --verbose