nvidia-nvtx
NVIDIA Tools Extension
Decision gist · record as of 2026-08-14
Yes, if you are actively profiling NVIDIA GPU code with Visual Profiler. The package is lightweight, actively maintained, has no runtime dependencies, and is widely used in the ML/scientific computing ecosystem (top 1000 PyPI). Install only if you have CUDA and Visual Profiler available; otherwise it provides no value.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires NVIDIA CUDA toolkit and Visual Profiler to be installed separately to capture and visualize the annotations.
- Medium install friction due to platform-specific wheels (x86_64 Linux, aarch64 Linux, Windows x64).
- Package is actively maintained with a recent release 80 days ago and supports Python 3.5 through 3.11.
License · maintenance · safety
(unclear)
last release 2026-05-26 (80 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 38,767,974 downloads/mo, #706 on PyPI
Alternatives
Verify before relying
pip install nvidia-nvtx
import nvidia_nvtx as nvtx
# Mark a code range for profiling
with nvtx.annotate("my_function"):
# your code here
pass- Whether the package works on non-NVIDIA systems or requires NVIDIA GPU hardware to function.
- Whether annotations are captured at runtime or only when profiler is actively running.
- Performance overhead of annotation calls during normal execution.
What it is and what it does
NVIDIA NVTX is a C-based instrumentation library wrapped for Python that lets you mark specific events, code ranges, and resources in your application for performance analysis. When your code runs under NVIDIA's Visual Profiler, these annotations appear as labeled markers in the profiling timeline, making it easier to correlate performance bottlenecks with specific functions or operations. The package has no runtime dependencies and supports Python 3.5 and later on Linux (x86_64 and aarch64) and Windows (x64).
It's primarily used in machine learning and scientific computing workflows where developers need fine-grained visibility into GPU-accelerated code execution. The library is actively maintained, classified as Beta, and targets developers, educators, and researchers working with CUDA and deep learning frameworks.
Use it for
- Mark expensive GPU kernel calls in deep learning training loops to identify performance bottlenecks in profiler output.
- Annotate data preprocessing and transfer stages to visualize where time is spent in end-to-end ML pipelines.
- Label custom CUDA operations in scientific computing code to correlate them with system-level performance metrics.
- Instrument multi-stage inference pipelines to track latency contributions from different model components.
- Trace resource allocation and deallocation patterns to detect memory management issues in GPU applications.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are actively profiling NVIDIA GPU code with Visual Profiler.
The package is lightweight, actively maintained, has no runtime dependencies, and is widely used in the ML/scientific computing ecosystem (top 1000 PyPI). Install only if you have CUDA and Visual Profiler available; otherwise it provides no value.
Install
nvidia-nvtx on PyPI
Before you install
Medium install friction due to platform-specific wheels (x86_64 Linux, aarch64 Linux, Windows x64). Package is actively maintained with a recent release 80 days ago and supports Python 3.5 through 3.11.
Requires NVIDIA CUDA toolkit and Visual Profiler to be installed separately to capture and visualize the annotations.
Quickstart
pip install nvidia-nvtx
import nvidia_nvtx as nvtx
# Mark a code range for profiling
with nvtx.annotate("my_function"):
# your code here
passVerify before relying
- Whether the package works on non-NVIDIA systems or requires NVIDIA GPU hardware to function.
- Whether annotations are captured at runtime or only when profiler is actively running.
- Performance overhead of annotation calls during normal execution.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 80 days since the last release |
| First released | |
| Downloads | 38,767,974 / month, #706 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchNatural Language :: EnglishOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.5Programming Language :: Python :: 3.6Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: Libraries |
Evidence: nvidia_nvtx-13.3.29-py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl; nvidia_nvtx-13.3.29-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl; nvidia_nvtx-13.3.29-py3-none-win_amd64.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 › “nvtx event marking”
- nvidia-nvtxProvides a Python API for annotating events and code ranges in…
- nvtxnvtx annotates Python code regions with named markers and colors for…
- nvidia-nvtx-cu11Provides a C-based API for annotating events, code ranges, and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also nvidia-nvtx-cu12 · nvtx · nvidia-nvtx-cu11 · cupti-python · nvidia-cuda-cupti · viztracer · nvidia-cuda-cupti-cu12 · scalene · torch-tb-profiler · austin-dist