skills.rest
martialarcon
martialarconCOMMUNITY
Explore all skills by this author →
GitHub

runtime-test

Execute Python code in a GPU/CUDA Docker container and report performance metrics.

1|Updated Feb 15, 2026
Search Tags:#performance#python#docker#gpu#cuda#jetson
One-click install
npx skills add https://github.com/martialarcon/claude-code-expert --skill runtime-test
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: runtime-test
Source: https://github.com/martialarcon/claude-code-expert/tree/main/.claude/skills/runtime-test
Command: npx skills add https://github.com/martialarcon/claude-code-expert --skill runtime-test

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill allows you to execute Python code within a specialized Docker container that has access to GPU/CUDA capabilities, essential for performance-intensive tasks like computer vision and AI inference.

Core Features & Use Cases

  • GPU/CUDA Execution: Run Python scripts that leverage NVIDIA GPUs for accelerated processing.
  • Jetson Performance Metrics: Collect and report performance data such as GPU utilization and temperature.
  • Use Case: Test a new object detection model using a Python script that processes video frames on the Jetson's GPU, then analyze the reported performance metrics to ensure efficiency.

Quick Start

Execute the Python script located at src/camera_capture.py within the runtime container.

Frequently Asked Questions about runtime-test

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Python code in a Docker container with GPU and CUDA support?▼

You can run Python code in a GPU-enabled Docker container by executing scripts inside the active project-runtime container, leveraging CUDA and TensorRT for accelerated vision, inference, and video processing tasks.

How do I benchmark GPU performance and estimate FPS on a Jetson device?▼

To benchmark GPU performance and estimate FPS on a Jetson device, run your Python script in the runtime container with benchmark mode enabled to collect and report GPU usage, temperature, and estimated frames per second metrics.

Do I need a specific Docker container to execute TensorRT vision processing scripts?▼

Yes, executing TensorRT vision processing scripts requires the project-runtime Docker container to be active and accessible, as it provides the necessary GPU, CUDA, and TensorRT environment for your Python code.

Can I use this to test object detection models processing video frames on a GPU?▼

Yes, you can use this to test object detection models processing video frames on a GPU, and with benchmark mode enabled, you can analyze reported performance metrics to ensure your inference and video processing tasks are efficient.

What limitations exist when running Python scripts in a GPU-enabled container?▼

A key limitation is that the runtime container depends on the project-runtime Docker container being active and accessible; without it, executing Python scripts or collecting GPU performance metrics like temperature and FPS is not possible.

Related Skills

Explore More Software Engineering Skills→
NVIDIANVIDIA
13.2k

trt-cpp-runtime-quickstart

Load and run TensorRT engines with the modern C++ Runtime API.

Official
Intermediate
OpenMOSSOpenMOSS
410

sglang-diffusion-performance

Optimize SGLang diffusion performance settings for a model, GPU, and VRAM budget.

Official
Intermediate
ZurybrZurybr

video-processing

Analyze video frames and extract temporal events using OpenCV.

Community
Advanced
gqf2008gqf2008

llama-cpp

Run local LLM inference on CPU and GPU with GGUF quantization.

Community
Advanced