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:

• Platform and Software Support: Supported operating systems, CUDA versions, cuDNN, Python API, ONNX parser, and control flow features

• Hardware and Precision Support: GPU architectures with their supported precision modes (TF32, FP32, FP16, FP8, FP4, BF16, INT8) and Deep Learning Accelerator (DLA) availability

• Compute Capability: GPU compute capabilities supported on each platform

• Compiler and Python Versions: Required compiler and Python versions for building and using TensorRT on each platform

• ONNX Operator Support: Links to comprehensive ONNX operator compatibility documentation

Documentation Structure

This documentation is organized into the following sections:

NVIDIA TensorRT 10.x Support Matrix

• 10.12.0 (Latest)
• 10.11.0
• 10.10.0
• 10.9.0
• 10.8.0
• 10.7.0
• 10.6.0
• 10.5.0
• 10.4.0
• 10.3.0
• 10.2.0
• 10.1.0
• 10.0.1
• 10.0.0 Early Access