Skip to content

Graiphic/GO-Whitepapers

Repository files navigation

Graiphic GO Whitepaper Series

Unified graph computing for AI, logic, hardware, and deployable systems.

This library gathers Graiphic's GO whitepapers into a single GitHub Pages experience built around ONNX as a graph format, ONNX Runtime as an execution layer, and SOTA as the visual orchestration environment.

Graph Computing AI Orchestration Hardware Abstraction Informed Machine Learning

Collection Overview

Each whitepaper lives in its own folder with:

  • a Markdown presentation page
  • the original PDF
  • supporting illustrations and diagrams

Use the sidebar to jump directly between documents or open the PDF versions from the download section.

SOTA GO

SOTA GO cover

Theme: ONNX-native authoring, compilation, and orchestration inside LabVIEW.

The foundational visual environment for building, training, deploying, and orchestrating ONNX graphs across the Graiphic stack.

GO HW

GO HW cover

Theme: Hardware orchestration through ONNX.

Extends the graph model beyond inference into deterministic orchestration of I/O, DMA, timing, and heterogeneous hardware targets.

GO GenAI

GO GenAI cover

Theme: Unified orchestration of Generative AI through ONNX.

Transforms fragmented GenAI stacks into a single graph-based system that combines models, tokenizers, logic, memory, and runtime orchestration.

GO IML

GO IML cover

Theme: Informed Machine Learning inside the ONNX graph.

Introduces a knowledge-aware training and deployment approach where physics, logic, constraints, and expert priors become native graph elements.

Whitepapers

1. SOTA GO - The LabVIEW IDE for Graph Computing

SOTA GO is the operational foundation of Graiphic's technology stack. It provides a unified visual cockpit where engineers can author, inspect, train, optimize, deploy, and operate ONNX graphs directly inside LabVIEW.

2. GO HW - From Models to Systems

GO HW extends ONNX beyond model execution into deterministic system orchestration. It introduces graph-level hardware primitives for GPIO, DMA, ADC, DAC, timers, synchronization, and energy-aware deployment.

3. GO GenAI - From Fragmentation to Orchestration

GO GenAI reframes generative AI as a system orchestration problem. Models, tokenizers, control flow, memory, preprocessing, postprocessing, and hardware execution become part of one executable graph.

4. GO IML - From Theory to Superiority

GO IML introduces Informed Machine Learning as a graph-native capability where priors, symbolic logic, physical constraints, and expert knowledge directly shape the learning process and final deployed system.

Learn More

Contact

License

Released under CC BY-NC-SA 4.0
© 2025 Graiphic - https://www.graiphic.io

Releases

No releases published

Packages

 
 
 

Contributors