Support Matrix

The TensorRT Support Matrix provides comprehensive information about platform compatibility, hardware requirements, and feature availability for each TensorRT release. Each support matrix includes:

• Hardware and Precision Support: GPU architectures with their supported precision modes (FP32, FP16, FP8, FP4, BF16, INT8)

• Compute Capability: GPU compute capabilities supported on each platform

• Compiler and Python Versions: Compiler version and Python support for building and using TensorRT on each platform

Documentation Structure

This documentation is organized into the following sections:

NVIDIA TensorRT-RTX 1.x Support Matrix

• 1.4 (Latest)
• 1.3
• 1.2
• 1.1
• 1.0