Get the newsletter
IBM · AI / ML · Filed Feb 10, 2025 · USPTO published Aug 13, 2026 · Aug 13 release

IBM Patents a System for Splitting AI Models Across Multiple Storage Nodes

Running a large AI model usually means one machine has to hold the whole thing. IBM's new patent describes a way to slice a model into numbered pieces and spread those pieces across a network of storage hubs, each holding only its assigned chunk.

Distributed storage of machine learning model blocks across multiple nodes managed by an orchestrator. Drawing from patent filing US 2026/0236306 A1.
Distributed storage of machine learning model blocks across multiple nodes managed by an orchestrator.All 13 drawings ↓
Publication number
US 2026/0236306 A1(US20260236306A1)
Applicant
INTERNATIONAL BUSINESS MACHINES CORPORATION
Filed · Published
Feb 10, 2025 · Aug 13, 2026
Inventors
Guangya Liu, Peng Li, Feng Li, Jin Chi He
Status when we published
Waiting for an examiner
Document
20 claims
US classification
718/104

How IBM wants to distribute AI model storage

Today, when a company wants to deploy a large AI model, it typically needs a single server (or tightly coupled cluster) powerful enough to hold the entire model in memory. That's expensive, inflexible, and hard to scale.

IBM's patent describes a coordinator, called a model hub orchestrator, that chops an AI model into sections and farms each section out to a different storage node on the network. Each section gets a number so the system always knows what order the pieces go in. When the AI needs to run, it pulls the right pieces from the right nodes in sequence.

The idea is to make it easier to deploy large models without requiring any single machine to carry the full load. Think of it like breaking a very long book into chapters and storing each chapter in a different filing cabinet. You can still read the whole book; you just grab one chapter at a time.

From the filing · CLAIM 1
… assigning each processing block an index indicating a position of the processing block within a sequential arrangement of the plurality of processing blocks of the machine learning model …

Translation: The system breaks the AI model into numbered pieces so it knows exactly how to reassemble them later.

How the model scheduler indexes and places blocks

The patent centers on a model hub orchestrator, a software coordinator that sits between a client device (the machine submitting an AI model for deployment) and a collection of model hubs (network-connected storage nodes).

Here is the core sequence the patent describes:

  • The orchestrator's model scheduler receives a request from a client and identifies all the processing blocks that make up a machine learning model. A processing block is essentially a discrete layer or functional segment of the model.
  • Each block is assigned an index, a number that records its position in the model's sequential order, so the system can reconstruct the full pipeline at inference time.
  • The scheduler then picks which model hubs will store which blocks, spreading the model across multiple nodes rather than keeping it on one machine.
  • Finally, the blocks are transferred from the client device to their assigned hubs.

The patent does not describe in detail how the model runs inference once it is distributed; its focus is the placement and transfer phase. The indexed ordering is the key mechanism: without knowing which block comes first, second, or third, a distributed system cannot execute the model correctly.

From the filing · THE ABSTRACT
The model scheduler selects one or more model hubs communicatively coupled with the model hub orchestrator to store different ones of the plurality of processing blocks.

Translation: A central manager decides which remote servers will hold the specific parts of the AI model.

What distributed AI model storage means for enterprise

For enterprises running large AI models, storage and memory costs are a real constraint. If IBM can make it practical to spread a single model across cheaper, commodity storage nodes rather than a single high-memory server, that could lower the barrier for companies that want to self-host AI instead of paying for cloud inference APIs.

The patent sits squarely in the infrastructure layer of AI deployment, an area where IBM has historically competed with cloud providers like AWS and Azure. It is early-stage work, covering the orchestration logic without specifying the hardware or the inference runtime, and that gap between a placement patent and a finished product is not trivial. Still, IBM's push into AI model distribution is part of a broader wave of enterprise AI infrastructure filings tracked among the newest Big Tech patents across the industry.

Source: US 2026/0236306 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time IBM patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 13 sheets

13 drawing sheets from US 2026/0236306 A1 · click any drawing to enlarge

Computer system network infrastructure overview, drawing sheet 1 from US 2026/0236306 A1
Sheet 1 Computer system network infrastructure overview
Model hub orchestrator component architecture, drawing sheet 2 from US 2026/0236306 A1
Sheet 2 Model hub orchestrator component architecture
Detailed orchestrator component interaction pathways, drawing sheet 3 from US 2026/0236306 A1
Sheet 3 Detailed orchestrator component interaction pathways
Steps for identifying model processing blocks, drawing sheet 4 from US 2026/0236306 A1
Sheet 4 Steps for identifying model processing blocks
Sequence diagram for pushing model data, drawing sheet 5 from US 2026/0236306 A1
Sheet 5 Sequence diagram for pushing model data
Initial storage distribution of model one, drawing sheet 6 from US 2026/0236306 A1
Sheet 6 Initial storage distribution of model one
Metadata store mapping for model one, drawing sheet 7 from US 2026/0236306 A1
Sheet 7 Metadata store mapping for model one
Extended storage distribution of model two, drawing sheet 8 from US 2026/0236306 A1
Sheet 8 Extended storage distribution of model two
Show the other 5 sheets
IBM Patents a System for Splitting AI Models Across Multiple Storage Nodes patent drawing, sheet 9
Sheet 9
IBM Patents a System for Splitting AI Models Across Multiple Storage Nodes patent drawing, sheet 10
Sheet 10
IBM Patents a System for Splitting AI Models Across Multiple Storage Nodes patent drawing, sheet 11
Sheet 11
IBM Patents a System for Splitting AI Models Across Multiple Storage Nodes patent drawing, sheet 12
Sheet 12
IBM Patents a System for Splitting AI Models Across Multiple Storage Nodes patent drawing, sheet 13
Sheet 13
Patent filing page

More in AI training & infrastructure

All 316 AI training & infrastructure patents →

Watchlists this filing belongs to

All watchlists →