Skills
.Work. You
Rest

trt-strong-typing-migration

Official

Streamline TensorRT builds by converting to strongly-typed networks.

Software Engineering#build automation#tensorrt#network migration#strong typing#onnx auto-cast
AuthorNVIDIA
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the process of migrating TensorRT builds from weak to strong typing, ensuring compatibility with the latest TensorRT versions.

Core Features & Use Cases

  • Weak to Strong Typing Conversion: Automate the transformation of weakly-typed builds to strongly-typed networks.
  • AutoCast for ONNX Files: Provides AutoCast functionality for ONNX files to support mixed precision.
  • Rebuilding and Validating: Ensures engines are rebuilt correctly and validated against baseline results.

Quick Start

Use the 'trt-strong-typing-migration' skill to migrate a weakly-typed Python network definition to a strongly-typed one.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: trt-strong-typing-migration
Download link: https://github.com/NVIDIA/TensorRT/archive/main.zip#trt-strong-typing-migration

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.