Overview

Purem is an advanced high-performance computational library optimized for vectorized mathematical operations. This project focuses on efficient execution of element-wise transformations, including softmax, exp, and other mathematical functions, leveraging highly optimized assembly code for modern architectures.

Installation

Install the Purem Python package via pip:

    pip install purem
    

Quickstart

1. Import and Initialize

    from purem import purem

    purem.configure(license_key='<your-license-key>')  # Auto-downloads and configures the native Purem engine.
    purem.softmax(array)  # Run purem on the input array.
    

License-Based Activation

The system will download the licensed native Purem engine.

    from purem import purem

    purem.configure(license_key='<your-license-key>')
    

All functions will become available instantly after initialization.

Without a valid license key:

• No native Purem engine will be downloaded

Available Functions

    from purem import purem

    # Transforms a list of numbers into a probability distribution.
    # Each output value is between 0 and 1, and all outputs sum to 1.
    # Commonly used in classification tasks to interpret scores as probabilities.
    purem.softmax([...])
    ...
    

Packaging Notes

The Purem Python package does not include the native Purem engine. You are required to:

• Use a license key to download it dynamically
• For evaluation on Apple Silicon environments, use the purem-ARM64-license key.

Distribution and Licensing

The native Purem engine is distributed exclusively through license-based activation or your user profile.

You can view the Terms of Service by following this link.

Full Example

    # Import required modules
    import numpy as np
    from purem import purem

    # Automatic setup using license key
    try:
        purem.configure(license_key='<your-license-key>')
    except Exception as e:
        print(f"Setup failed: {e}")

    data = np.array([1.0, 2.0, 3.0], dtype=float)
    output = purem.softmax(data)

    print(output)
    

Advanced Usage & API Docs

Coming soon...