tensorrt-cu13-bindings

What it is and what it does

tensorrt-cu13-bindings is a low-level Python wrapper around NVIDIA's TensorRT 11.2.1.2 inference engine, compiled specifically for CUDA 13. It exposes TensorRT's C++ API to Python, allowing developers to build, optimize, and deploy deep learning models for high-performance inference on NVIDIA GPUs. The package is a binary distribution with no runtime dependencies listed, meaning it bundles the necessary compiled libraries.

This is a specialized package for developers who need direct access to TensorRT's inference capabilities. It supports modern Python versions (3.8 through 3.14) across Linux x86_64, Linux aarch64, and Windows x86_64 platforms. The package is actively maintained and part of NVIDIA's broader TensorRT ecosystem, which includes support for importing models from ONNX, PyTorch, and other frameworks.

Use it for:

• Optimize and deploy pre-trained deep learning models for production inference on NVIDIA GPUs.
• Build custom inference engines using TensorRT's network definition API for latency-critical applications.
• Accelerate LLM, vision, NLP, and audio model inference workflows on NVIDIA hardware.
• Integrate GPU-accelerated inference into Python applications without external C++ dependencies.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides Python bindings for NVIDIA TensorRT 11.2.1.2 compiled for CUDA 13, enabling deep learning inference acceleration on compatible GPUs.

Yes, if you need TensorRT inference on CUDA 13 and your deployment platform matches the supported architectures (Linux x86_64/aarch64 or Windows x86_64). Verify the proprietary license terms for your use case first. The package is actively maintained, has no known vulnerabilities, and is part of a mature NVIDIA ecosystem. If you are unsure whether to use this or the main tensorrt package, check NVIDIA's documentation on package variants.

Install

tensorrt-cu13-bindings on PyPI

pip install tensorrt-cu13-bindings

uv add tensorrt-cu13-bindings

poetry add tensorrt-cu13-bindings

Installing tensorrt-cu13-bindings

Before you install

Medium install friction due to platform-specific wheel distribution (x86_64 Linux, aarch64 Linux, Windows only) and CUDA 13 runtime dependency. Package is actively maintained with recent releases and no known vulnerabilities.

License in practice

Licensed under a proprietary license with unclear treatment. Verify licensing terms with NVIDIA before using in commercial or redistributed projects.

Quickstart

pip install tensorrt-cu13-bindings

import tensorrt as trt
logger = trt.Logger(trt.Logger.WARNING)

Requires CUDA 13 runtime and compatible NVIDIA GPU; only available for Python 3.8–3.14 on Linux x86_64, Linux aarch64, or Windows x86_64.

Verify before relying

• Whether this package is the correct entry point or if the main tensorrt package should be preferred instead.
• Exact scope of proprietary license restrictions and whether it permits commercial use.
• Whether CUDA 13 is required or if other CUDA versions are supported via separate packages.

Package facts

Evidence: tensorrt_cu13_bindings-11.2.1.2-cp310-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp310-none-manylinux_2_35_aarch64.whl; tensorrt_cu13_bindings-11.2.1.2-cp310-none-win_amd64.whl; tensorrt_cu13_bindings-11.2.1.2-cp311-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp311-none-manylinux_2_35_aarch64.whl; tensorrt_cu13_bindings-11.2.1.2-cp311-none-win_amd64.whl; tensorrt_cu13_bindings-11.2.1.2-cp312-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp312-none-manylinux_2_35_aarch64.whl; tensorrt_cu13_bindings-11.2.1.2-cp312-none-win_amd64.whl; tensorrt_cu13_bindings-11.2.1.2-cp313-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp313-none-manylinux_2_35_aarch64.whl; tensorrt_cu13_bindings-11.2.1.2-cp313-none-win_amd64.whl; tensorrt_cu13_bindings-11.2.1.2-cp314-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp314-none-manylinux_2_35_aarch64.whl; tensorrt_cu13_bindings-11.2.1.2-cp314-none-win_amd64.whl; tensorrt_cu13_bindings-11.2.1.2-cp38-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp38-none-manylinux_2_35_aarch64.whl; tensorrt_cu13_bindings-11.2.1.2-cp38-none-win_amd64.whl; tensorrt_cu13_bindings-11.2.1.2-cp39-none-manylinux_2_28_x86_64.whl; tensorrt_cu13_bindings-11.2.1.2-cp39-none-manylinux_2_35_aarch64.whl

Keywords: nvidia, tensorrt, deeplearning, inference

Tags

More Artificial Intelligence packages