Profiling and trace analysis SDK
Project description
nCompass Python SDK
Profiling and trace analysis SDK. Built by nCompass Technologies.
Features
- 📊 Advanced Profiling - Built-in performance monitoring and health metrics
- 🤖 AI-Powered Analysis - Intelligent trace analysis and bottleneck identification
- 🔄 Iterative Optimization - Progressive profiling workflow for targeted improvements
- 🎯 AST-Level Instrumentation - Automatic code instrumentation without manual changes
- ⚡ Production-Ready - Separate development and production configurations
Installation
Install via pip:
pip install ncompass
Examples
Refer to our open source GitHub repo for examples.
Documentation
- Getting Started - Installation and basic usage
- API Reference - Complete API documentation
- Advanced Usage - Advanced features and best practices
- Examples - Working code examples
Online Resources
- 🌐 Website: ncompass.tech
- 📚 Documentation: docs.ncompass.tech
- 💬 Community: community.ncompass.tech
- 🐛 Issues: GitHub Issues
Why nCompass?
- AI assisted bottleneck identification
- Intelligent profiling marker suggestions
- Progressive optimization guidance
Requirements
- Python 3.9 or higher
- PyTorch 2.0+ (optional, for torch profiling features)
- CUDA-capable GPU (optional, for GPU profiling)
Examples
See the examples directory for complete working examples:
- basic_usage.py - Simple profiling session
- profiling_session.py - Complete workflow
- advanced_tracing.py - Iterative optimization
Development
Coverage & Quality Tools
All development and coverage tools are in the tools/ directory:
# Install development dependencies
pip install -e ".[dev]"
# Run coverage checks (from tools/ directory)
cd tools
make all-checks # Run all checks
make coverage # Unit test coverage
make docstring-coverage # Docstring coverage
make type-stats # Type hint coverage
make lint # Run linters
make format # Auto-format code
See tools/COVERAGE.md for comprehensive documentation.
Project Structure
ncompass/
├── pyproject.toml # Project config (only root file)
├── ncompass/ # Main package
├── tests/ # Test suite
├── examples/ # Usage examples
├── docs/ # Documentation
└── tools/ # All development tools
├── Makefile
├── COVERAGE.md
├── pyrightconfig.json
└── .coveragerc
License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Support
- Documentation: docs.ncompass.tech
- Community Forum: community.ncompass.tech
- Email: support@ncompass.tech
About nCompass Technologies
We are building tools that allow GPU kernel developers save hours of dev time every week. Write code that runs twice as fast, twice as quickly.
Learn more at ncompass.tech.
Made with ⚡ by nCompass Technologies
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ncompass-0.1.8.tar.gz.
File metadata
- Download URL: ncompass-0.1.8.tar.gz
- Upload date:
- Size: 27.6 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a47c206c8c294cc7be41f288e4775a2056789685cf96b3a38778d44a60f469fa
|
|
| MD5 |
2a484ff7b16f34c672c0a06a2db6a2e8
|
|
| BLAKE2b-256 |
71f76d5f3928e3e2538ed0b5295aa57349a63795ba1a1cb8427fbd39f86e3d22
|
File details
Details for the file ncompass-0.1.8-py3-none-any.whl.
File metadata
- Download URL: ncompass-0.1.8-py3-none-any.whl
- Upload date:
- Size: 76.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b216c80d633fa2de2792ed60bb44753e336e45911501c1fce0e4c2ecfb447c57
|
|
| MD5 |
c5bb033ff11b3fe73bb92f2ccbb2d82d
|
|
| BLAKE2b-256 |
46c709a0d402fb36a9eaf2882d753342055ea34f1da5cacdc5d18c2d8d5376eb
|