# The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN

arXiv: https://arxiv.org/abs/2609.07843 · HTML: https://mlsanity.com/paper/2609.07843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [dApps: Distributed Applications for Real-time Inference and Control in O-RAN](https://mlsanity.com/paper/2203.02370/) (2022)
- [dApps: Enabling Real-Time AI-Based Open RAN Control](https://mlsanity.com/paper/2501.16502/) (2025)
- [Design of a Standard-Compliant Real-Time Neural Receiver for 5G NR](https://mlsanity.com/paper/2409.02912/) (2024)
- [InterfO-RAN: Real-Time In-band Cellular Uplink Interference Detection with GPU-Accelerated dApps](https://mlsanity.com/paper/2507.23177/) (2025)
- [Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA Aerial Testbed](https://mlsanity.com/paper/2512.06493/) (2025)
- [NVIDIA AI Aerial: AI-Native Wireless Communications](https://mlsanity.com/paper/2510.01533/) (2025)
- [Performance Characterization of dApps in Open Radio Access Networks](https://mlsanity.com/paper/2605.05426/) (2026)
- [GPU-Resident CUDA Acceleration for OCUDU 5G PHY and O-RAN Fronthaul: Architecture and Preliminary Performance](https://mlsanity.com/paper/2608.04338/) (2026)

## Abstract (arXiv)

Machine learning has shown its largest gains in the band below 10 ms inside a 3GPP new radio (NR) 5G distributed unit (DU): link adaptation, per-slot scheduling, channel estimation, and the receiver itself. No open platform has let independently built software run there. Prior dApp frameworks reached the band only as external observers of an export stream. This paper is a guided introduction to the OCUDU dApp platform, an open runtime and E3 interface under which signed AI-RAN applications execute inside a production DU under three timing contracts: resident on the GPU receive chain (Class A), inside the scheduler's 100 us admitted deadline (Class B), or as never-blocking observers whose results the scheduler consumes (Class C). The conventional path is never displaced, and every authority is typed, validated, and operator-bounded. The paper explains how the runtime, the embedded E3 agent, and the three public repositories fit together; shows a dApp's source, its signed package, and its lifecycle state machine; defines the contracts a module is written against; and shows how one management surface serves a Python script, an operator's console, and an LLM agent. On a GB10 gNB with attached handsets, dApps of all three classes, including an out-of-tree neural equalizer, ran together on a live cell without a single fallback, and equalizer variants were compared over the air by lifecycle operations alone. Every measured checkpoint is reported with its conditions and its gaps. Platform, SDK, and a zero-hardware quickstart are public under BSD-3-Clause-Clear as a preview release of the OCUDU AI-RAN Working Group 2, inviting feedback, new use cases, and independent vetting ahead of upstreaming into the OCUDU mainline.