Get the newsletter
Qualcomm · AI / ML · Filed May 16, 2025 · USPTO published Nov 19, 2026 · This week's release

Qualcomm Files Patent for Splitting One AI Model Across Several Phones and Laptops

Qualcomm's filing describes a way for several devices to share one AI model, switching how they divide the work between reading your question and writing the answer.

AI tasks divided across several linked devices so they can run complex programs together. Drawing from patent filing US 2026/0368486 A1.
AI tasks divided across several linked devices so they can run complex programs together.All 15 drawings ↓
Publication number
US 2026/0368486 A1(US20260368486A1)
Applicant
QUALCOMM Incorporated
Filed · Published
May 16, 2025 · Nov 19, 2026
Inventors
Qi XUE, Abhijit NAVALEKAR
Status when we published
Waiting for an examiner
Document
20 claims
US classification
706/15

What Qualcomm's device-sharing AI patent does

You're pasting a long document into an AI assistant on your phone and asking for a summary. Then you wait, because a model that big strains one phone's memory, battery and processing power.

Qualcomm's patent describes spreading that work across several devices, such as phones, tablets or laptops, and changing how the work is divided partway through. Reading your question goes fastest when each device takes a stretch of the model, like stations on an assembly line. Writing the answer goes fastest when every device takes a slice of every step and they all work at once.

A built-in speed chart tells the system which method to use at each stage, and how many devices to bring in.

From the filing · CLAIM 1
determine to process an input embedding to generate key-value pairs using a pipeline parallelization mode of the apparatus; process the input embedding to generate the key-value pairs based on the pipeline parallelization mode of the apparatus …

Translation: The device figures out how to break down the AI task and starts processing the first part of the workload.

How the work switches between two splitting modes

The patent covers a device that runs an AI language model in two stages and shares the work differently in each. First, the model reads your prompt and saves key-value pairs, notes about your question that it can reuse so it doesn't reread everything for each new word. The filing calls this the prefill stage.

For that stage it uses pipeline parallelism: the model's layers are divided into groups and each device runs one group, like stations on an assembly line. The filing's example has three devices with ten layers each. To write the answer, it switches to tensor parallelism: every device holds a slice of each layer, and they combine partial results after every layer. The example uses two devices here, and the saved notes move between their caches while other work continues.

The choice rests on numbers. For the first stage, the device compares token latency (the wait until the first piece of the answer appears) and picks the lower. For the writing stage, it compares decode rate (how fast new pieces come out) and picks the higher. Both come from a lookup table that factors in link speed between devices, prompt size, device count and the expected size of the saved notes.

What this means for AI on phones and laptops

The practical idea is that a few devices working together could run an AI model too big for any one of them. The filing's background describes exactly that limit on portable electronics: power, memory and processing. It also offers a way to share the load that does not depend only on cloud servers, though the filing lists servers among the devices that could take part.

For you, the payoff would be a shorter wait before an answer starts and faster writing once it does. The filing describes the speed chart and the switching logic but gives no real timing figures, so how much faster this would be is unknown.

That makes this Qualcomm's 69th filing we've tracked since July in the AI chip wars, adding to work like the chatbot memory shortcut and skipping conversation reruns.

Source: US 2026/0368486 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 Qualcomm 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 · 15 sheets

15 drawing sheets from US 2026/0368486 A1 · click any drawing to enlarge

Core chip parts that power smart features on a device, drawing sheet 1 from US 2026/0368486 A1
Sheet 1 Core chip parts that power smart features on a device
Slicing an AI model horizontally across multiple gadgets, drawing sheet 2 from US 2026/0368486 A1
Sheet 2 Slicing an AI model horizontally across multiple gadgets
Passing an entire prompt down a chain of devices, drawing sheet 3 from US 2026/0368486 A1
Sheet 3 Passing an entire prompt down a chain of devices
Breaking a prompt into chunks so devices work at once, drawing sheet 4 from US 2026/0368486 A1
Sheet 4 Breaking a prompt into chunks so devices work at once
Exchanging data between devices running split AI pieces, drawing sheet 5 from US 2026/0368486 A1
Sheet 5 Exchanging data between devices running split AI pieces
Speed estimates for different device setups and prompt sizes, drawing sheet 6 from US 2026/0368486 A1
Sheet 6 Speed estimates for different device setups and prompt sizes
Finding the device count that finishes a task fastest, drawing sheet 7 from US 2026/0368486 A1
Sheet 7 Finding the device count that finishes a task fastest
Picking different device counts for reading and answering, drawing sheet 8 from US 2026/0368486 A1
Sheet 8 Picking different device counts for reading and answering
Show the other 7 sheets
Three devices hand off work before two write the reply, drawing sheet 9 from US 2026/0368486 A1
Sheet 9 Three devices hand off work before two write the reply
Combining partial calculations from other phones to finish a step, drawing sheet 10 from US 2026/0368486 A1
Sheet 10 Combining partial calculations from other phones to finish a step
Switching teamwork strategies between reading prompts and generating text, drawing sheet 11 from US 2026/0368486 A1
Sheet 11 Switching teamwork strategies between reading prompts and generating text
Basic structure of a multi-step digital brain, drawing sheet 12 from US 2026/0368486 A1
Sheet 12 Basic structure of a multi-step digital brain
An image-scanning model breaking down a street photo, drawing sheet 13 from US 2026/0368486 A1
Sheet 13 An image-scanning model breaking down a street photo
The text-generating engine that powers modern chatbots, drawing sheet 14 from US 2026/0368486 A1
Sheet 14 The text-generating engine that powers modern chatbots
Hardware components inside a connected phone or laptop, drawing sheet 15 from US 2026/0368486 A1
Sheet 15 Hardware components inside a connected phone or laptop
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.