https://eureka.patsnap.com/resources/blog/rd-blog/serverless-function-gpu-accelerator-resource-scheduling-patent-landscape/ · Patsnap · data cut-off 2026-10-20 · downloaded from the live page
Patent Landscape · Software & Cloud Systems

Serverless Function GPU Accelerator Resource Scheduling Patents

Analysis of 12 patent families on serverless GPU accelerator scheduling: filer spread, IPC mix and filing activity through 2026.

19
Published Records
12
Simple Patent Families
32%
In Force at Cut-off
US
Leading Jurisdiction

19 published records collapse into 12 simple (DOCDB) families; the difference is the same invention filed in more than one country. In force = 6 of 19 records still granted and maintained at the data cut-off; the rest are pending, withdrawn, refused or lapsed.

  • 12 simple patent families and 19 published records make up this dataset, with no date limit applied to the search string.
  • Nine filers are tied at the top of the list, each named on 1 of the 12 simple patent families (8.3%), with all nine holding 2 or fewer families.
  • G06F (Electric digital data processing) appears on the largest share of families, 7 of 12 (58.3%), ahead of G06N (Computing based on AI models) at 4 of 12 (33.3%).
Check your own idea
Published byPatsnap Research··6 min readSourced from Patsnap Eureka
Overview

What this search covers

This dataset gathers published records whose text or classification links serverless or function-as-a-service computing to GPU, TPU or hardware accelerator terms alongside scheduling or allocation language. The search string carries no date limit, so the 19 published records and 12 simple patent families returned represent every matching record at retrieval, not a fixed filing window. A single invention can be filed in multiple jurisdictions, which is why records and families differ.

With 12 families in scope, this is a small pool. The figures below describe exactly what this search returned, they are a starting point for a closer search, not a map of a field.

Search scope at a glance
  1. CV RAMAN GLOBAL UNIV1
  2. HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD1
  3. POLITECNICO DI MILANO1
  4. VMWARE INC1
  5. INTEL CORP1
  6. HUAZHONG UNIV OF SCI & TECH1
  7. XELTA PTE LTD1
  8. VALLURUPALLI NAGESWARA RAO VIGNANA JYOTHI INST OF ENG & TECH1
  9. CHONGQING UNIV1

Ordered by volume only, not by importance or claim strength. Counted in simple (DOCDB) patent families, so one invention filed in several countries counts once. Names come from Patsnap's standardised assignee field as recorded on each document; subsidiaries and group companies are not merged. The icon before each name is read from the name itself (words such as University, Institute or Ltd); the data carries no organisation-type field, so treat it as a reading aid rather than a classification. Filings held by named individuals rather than organisations are removed where they can be identified (10 here); that identification is not exhaustive, so an individually held filing can still appear below. Either way those filings stay inside the totals above. This table shows the top 9 of the 9 filers returned for this search; the data endpoint returns at most 100 entities, so even that 9 is not the complete set of filers. A single family can name more than one filer, so these counts overlap and do not add up to the total.

Source: Patsnap Eureka. Assignee ranking and totals. Derived from one Patsnap search for Serverless Function GPU Accelerator Resource Scheduling Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Data & trends

Filing trend and technology composition

The figures below cover 19 published records and 12 simple patent families returned by this search, with a filing-trend chart that shows a recent window rather than the full scope.

Filing trend by earliest filing year (published records)

Published records by earliest filing year run from 2 in 2019 to a peak of 7 in 2020, with 4 recorded in 2026. Years from 2022 onward are still filling in as later publications arrive, so no slowdown or acceleration can be read from the recent end of the line.

Filing trend by earliest filing year (published records)02468220197202020212022202320242025420262022 onwards are shaded as still filling in: a filing is only visible once it publishes, up to 30 months after filing.

Counted in published records by earliest filing year, not de-duplicated into families. A filing is counted in the year it was filed, but it only becomes visible after it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. 2022 onwards are therefore still filling in and are shaded; no growth figure on this page uses them. Because this series counts documents rather than inventions, a rise can mean more inventions or the same inventions filed in more countries; this dataset cannot separate the two.

IPC subclass composition (share of 12 simple patent families)

G06F (Electric digital data processing) appears on 7 of the 12 families (58.3%), G06N (Computing based on AI models) on 4 (33.3%), and G06Q (Business, commerce & admin data processing) and H04L (Digital information transmission) on 2 each (16.7%). Because a family can carry more than one IPC class, these shares add up to more than 100% of the 12 families.

IPC subclass composition (share of 12 simple patent families)G06F · Electric digital data processi…758.3%G06N · Computing based on AI models433.3%G06Q · Business, commerce & admin dat…216.7%H04L · Digital information transmissi…216.7%G05B · Control & regulating systems18.3%G06T · Image data processing & genera…18.3%G10L · Speech & audio analysis/synthe…18.3%H04N · Pictorial communication (video…18.3%

Shares are the percentage of the 12 patent families in scope. One patent family can carry several IPC classes, so the shares add up to more than 100%.

Source: Patsnap Eureka. Filing trend and technology composition. Derived from one Patsnap search for Serverless Function GPU Accelerator Resource Scheduling Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.

Go deeper on Serverless Function GPU Accelerator Resource Scheduling Patent Landscape with Eureka

This page is one run against one query. Ask Eureka your own question about serverless function gpu accelerator resource scheduling patent landscape and every answer comes back with the patent numbers behind it.

Try Eureka
Representative filing

A record from the result set

From the search results
US20250285206A12025-09-11

GPU-sharing method and apparatus for serverless inference loads

HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

The abstract describes a method where GPU API calls triggered by serverless inference functions are intercepted and forwarded to an API proxy process, which manages and allocates resources across multiple GPUs connected to a CPU over a bus. The CPU directs API calls from each function of a given inference application to a pre-designated GPU runtime and stream pool, so that all functions belonging to the same application share consistent GPU access.This is the first record returned under the database's default ordering, not a ranking by citations, novelty or breadth.

US20250285206A1, patent drawing 1US20250285206A1, patent drawing 2
View full record

Selected as the first record the search returns under the database default order, then shown in full. It is not ranked by citations, claim breadth or commercial importance, and it is not a judgement about which filing in this space matters most.

Source: Patsnap Eureka. The first record the search returned, shown in full. Derived from one Patsnap search for Serverless Function GPU Accelerator Resource Scheduling Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Run it yourself

Put your own technology through the same analysis


  
Where to run it
Fastest

Eureka on the web

When you want the answer in the next five minutes.

The agent works the prompt against patents and technical literature, citing every source.

Run your analysis now →
For builders

MCP server & REST API

When it has to run inside your own pipeline.

Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.

Browse MCP servers →
Key figures

What the dataset shows

Three figures summarise the size, spread and technical composition of this search. Each is reported on its own terms, with the unit it was counted in.

Scope
12 families / 19 records
simple patent families / published records

Size of the dataset

The search returns 19 published records that de-duplicate to 12 simple patent families, with no date limit applied, so this is every matching record at retrieval rather than a bounded period.

Counted at retrieval, 2026-10-20
Filers
8.3%
largest single-row share

Largest filer share, tied nine ways

CV Raman Global University is named on 1 of the 12 simple patent families (8.3%), a figure shared by eight other listed filers also on 1 family each. All nine listed filers hold 2 or fewer families each; rows are not summed because one family can name more than one filer.

9 organisations listed, individuals excluded from this list but included in totals
Classification
58.3%
share of 12 families carrying G06F

G06F carries the largest share of families

G06F (Electric digital data processing) appears on 7 of the 12 simple patent families (58.3%), the largest share of any subclass reported. G06N (Computing based on AI models) follows at 4 families (33.3%). Shares add up to more than 100% because a family can carry more than one class.

Shares computed against the 12-family total
Legal status
32%
of 19 records granted and in force

Status at retrieval

6 of the 19 published records (32%) were granted and still in force at the retrieval date. The remaining records were not broken out by status, so no figure for pending, withdrawn or lapsed records is available here.

Status as of 2026-10-20
Eureka AI Agent
Looking for what nobody has claimed yet?

Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to serverless function gpu accelerator resource scheduling patent landscape, with the prior art for and against each one.

Find the white space →
Source: Patsnap Eureka. Derived observations on the same dataset. Derived from one Patsnap search for Serverless Function GPU Accelerator Resource Scheduling Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Next steps

Where to take this from here

The figures above describe what this search returned. Refining the query or reading individual claim sets is the next step for anyone acting on this.

Pull the granted claims directly

Family counts and abstracts describe what a filing discusses, not what its claims legally require. Reading the granted claim set is the only way to assess scope for a specific design.

Open a record in Eureka →

Widen or narrow the search terms

This dataset depends on specific terminology for serverless computing, accelerators and scheduling. Adjacent filings using different language for similar mechanisms will not appear under this exact string.

Rebuild the search in Eureka →

Track future publications

Records from 2022 onward are still filling in as later publications arrive, so recent activity in this space is understated at any given retrieval date.

Set up monitoring in Eureka →
Source: Patsnap Eureka. Suggested next steps. No new data: every figure named here is one of those above. Derived from one Patsnap search for Serverless Function GPU Accelerator Resource Scheduling Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
FAQ

Common questions

Answers are grounded in the same dataset. Derived from one Patsnap search for Serverless Function GPU Accelerator Resource Scheduling Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP

Research Serverless Function GPU Accelerator Resource Scheduling Patent Landscape in depth with Eureka

Go past this page: query the whole serverless function gpu accelerator resource scheduling patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.

Try Eureka
How this page was built, and what the numbers do and do not mean

Search. Every figure on this page comes from one Patsnap search, run once and not edited afterwards. This is the exact search string:

TAC:((serverless OR "function as a service") AND (GPU OR "hardware accelerator" OR TPU) AND (scheduling OR allocation))

Reading the field codes: TAC searches the title, abstract and claims of each record, not the full description. The search string sets no date limit, so the scope is every matching record in the database regardless of when it was filed. It is not restricted to recent years. How this string was built matters for how far the counts can be pushed. It was generated in batch from a topic list rather than hand-crafted for this page, and the result set is not manually screened. A keyword search over title, abstract and claims both over-captures (unrelated filings that happen to use the same words) and under-captures (the same invention written in different words). This page cannot measure either effect, so read every figure here as what this particular string returned, not as what exists in the field.

What is being counted. Two different units appear on this page and they are not interchangeable. The filer list and the technology split are counted in simple (DOCDB) patent families: one invention counts once however many countries it was filed in. The total, the jurisdiction split and the filing-year chart are counted in published records: the same invention counts once per publication. For this search that is 19 records and 12 families. Record counts reward filing in many jurisdictions; family counts do not. Shares are only ever taken against a denominator in the same unit, and each one names it.

Who the filers are. Names come from Patsnap's standardised assignee field, as recorded on the documents themselves. They are not rolled up to corporate group: a parent and its subsidiaries appear as separate entries, and a portfolio acquired from another company stays under the name on the document unless the assignment is reflected there. This list is meant to carry organisations, not people. Filings held by a named individual are identified by matching the assignee against the inventors on the same search, and, for names written in Chinese, Japanese or Korean characters, by the name carrying no organisational suffix; those are removed from the list (10 of them here). Neither test is exhaustive: the inventor list it matches against is itself capped, and a personal name written in Latin script with no organisational wording in it cannot be told apart from a short company name by rule. So an individually held filing can still appear in the list. Those filings stay inside every total and share on this page either way, so the listed entries can add up to less than the total. A record shown in full further down still names its assignee exactly as the patent office records it, including where that is a person: that name is how the record is identified and checked. What is left out of the ranking is people as ranked entries, not people as cited sources. The table shows the top 9 of the 9 filers returned, ordered by count alone; the data endpoint returns at most 100 entities, so even that 9 is not every filer. One patent family can name several filers and each is counted separately, so these rows are not slices of a divided whole: adding them together over-counts, and this page deliberately publishes no combined "top five" share for that reason. See every filer, individuals included

Dates. The year chart counts by earliest filing year, not publication year. A filing only becomes visible once it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. Measured across these pages, the year four back from today still holds only about 89% of its eventual count. 2022 onwards are therefore shaded on the chart as still filling in. The data behind this page was retrieved on 2026-10-20.

Legal status. "In force" counts documents whose legal status at retrieval was granted and maintained (6 of 19). Everything else is pending, withdrawn, refused, lapsed or not determinable, and those states are not broken out here because the underlying codes do not separate them cleanly. Legal status changes continuously and is reported per document, not per family. Get the status breakdown in Eureka

Classification. The technology split uses IPC subclasses (four characters, for example H01M). A single record usually carries several, so the shares add up to more than 100% and a record can appear in more than one bar. Subclass is a coarse grouping; it describes the field a record was classified into, not what the claims cover. Break the classes down to subgroup level

Who wrote the words. The tables, charts, counts, shares and patent numbers on this page are produced directly from the search result by a program; none of them are written or estimated by a language model. The surrounding prose, headings, FAQ answers and the answers in the question panel are drafted by a language model that is given those same figures and is not permitted to introduce others. Prose can still mis-describe a correct figure, so where the two disagree, the tables and charts are the record.

Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.

Patent data carries limitations that apply to every figure above. Recent filings are under-counted, because an application is not public until roughly 18 months after filing and database loading adds further delay. The search string defines and constrains everything shown: records that use different terminology, or that sit outside the fields searched, are absent and cannot be counted. Applicant names, classification codes, legal-status codes and citation records are taken as recorded and may contain errors, duplicates, omissions or stale entries. Ordering by volume is not a measure of quality, scope, enforceability or commercial value, and a larger portfolio is not a stronger one. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.

Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, validity or infringement search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. No attorney-client relationship is created by it. Any patent, commercial, or strategic decision should be verified independently against the primary records and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.

The question panel. The answers behind the suggested questions on this page were written when the page was generated, not in response to your click. The progress steps that play before an answer appears are an animation of how that analysis was done; nothing is being searched or computed at that moment. Typing your own question instead opens Patsnap Eureka, which does run it live.

Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.

Help us improve

Something wrong, out of date, or missing on this page? Tell us and it goes straight to the team that maintains it.