tensorrt-cu13-bindings
A high performance deep learning inference library
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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.
- 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 · maintenance · safety
Proprietary (unclear) — Licensed under a proprietary license with unclear treatment. Verify licensing terms with NVIDIA before using in commercial or redistributed projects.
last release 2026-07-30 (15 days) · last repo commit 2026-08-04 · 13,250 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 216,243 downloads/mo, #9,384 on PyPI
Alternatives
Verify before relying
pip install tensorrt-cu13-bindings
import tensorrt as trt
logger = trt.Logger(trt.Logger.WARNING)- 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.
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 on it.
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
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.
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.
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)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
| License | Proprietary unclear |
| Python support | Not specified |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 15 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 216,243 / month, #9,384 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersLicense :: Other/Proprietary LicenseProgramming Language :: Python :: 3 |
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
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “tensorrt cuda 13 python bindings”
- tensorrt-cu13-bindingsProvides Python bindings for NVIDIA TensorRT 11.2.1.2 compiled for…
- tensorrt-cu13-libsProvides NVIDIA TensorRT libraries for GPU-accelerated deep learning…
- tensorrt-cu13Provides Python bindings for NVIDIA TensorRT, a deep learning…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also tensorrt-cu12 · tensorrt-cu13 · tensorrt-cu12-bindings · tensorrt-cu13-libs · tensorrt · dyNET38 · tensorrt-cu12-libs · sit4onnx · transformer-engine-cu13 · transformer-engine-cu12