# US 2025/0097120 A1 · Techniques for artificial intelligence capabilities at a network switch

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0097120 A1
- Document ID: US20250097120A1
- Status: Published application
- Kind: A1
- Application number: 18/966,019
- Filed: 2024-12-02
- Published: 2025-03-20
- Earliest claimed: 2018-12-28
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Francesc GUIM BERNAT; Suraj PRABHAKARAN; Kshitij A. DOSHI; Brinda GANESH; Timothy VERRALL
- Web page: https://patentgrep.com/patent/US20250097120A1

## CPC

- H04L 41/16: using machine learning or artificial intelligence
- G06F 8/60: Software deployment
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/105: {Shells for specifying net layout}
- G06N 5/04: Inference or reasoning models
- H04L 41/0816: the condition being an adaptation, e.g. in response to network events
- H04L 41/344: Out-of-band transfers
- H04L 41/5012: {determining service availability, e.g. which services are available at a certain point in time}
- H04L 41/5019: Ensuring fulfilment of SLA
- H04L 41/5051: Service on demand, e.g. definition and deployment of services in real time
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/20: Ensemble learning
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Examples include techniques for artificial intelligence (AI) capabilities at a network switch. These examples include receiving a request to register a neural network for loading to an inference resource located at the network switch and loading the neural network based on information included in the request to support an AI service to be provided by users requesting the AI service.

## Claims

### Claim 1

At least one non-transitory machine readable medium storing instructions to be executed by at least one machine to be associated with a network switch, the network switch being configurable to comprise graphics processing unit (GPU) resource circuitry, data traffic processing circuitry, and management data processing circuitry, the network switch to be used in association with multiple tenants, the instructions, when executed by the at least one machine, resulting in the network switch being configured for performance of operations comprising:
receiving, at the network switch, management data and tenant service-related data, the tenant service-related data being configurable to correspond, at least in part, to artificial intelligence (AI) service requests of the multiple tenants, respective portions of the tenant service-related data being associated with respective of the multiple tenants;
generating, by the management data processing circuitry, configuration data, the configuration data to be based upon the management data, the configuration data to configure the GPU resource circuitry of the network switch to implement multi-tenant services associated with the respective of the multiple tenants, the multi-tenant services to be accessed by the respective of the multiple tenants based upon the respective portions of the tenant service-related data; and
routing, by the data traffic processing circuitry, the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch so as to permit the respective of the multiple tenants to access, based upon the respective portions of the tenant service-related data, the multi-tenant services associated with the respective of the multiple tenants;
wherein:
the data traffic processing circuitry is configurable to implement load balancing in association with the routing of the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch;
the multiple tenants are to be associated with respective tenant identification data; and
the data traffic processing circuitry is configurable to implement the routing of the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch based upon priority data.

### Claim 2 (depends on 1)

The at least one non-transitory machine readable medium of claim 1, wherein:
the network switch is to be comprised in a cloud-based network.

### Claim 3 (depends on 2)

The at least one non-transitory machine readable medium of claim 2, wherein:
the data traffic processing circuitry and/or the management data processing circuitry comprise central processing unit (CPU) core circuitry.

### Claim 4 (depends on 3)

The at least one non-transitory machine readable medium of claim 3, wherein:
the GPU resource circuitry of the network switch comprises multiple GPU processing cores.

### Claim 5 (depends on 4)

The at least one non-transitory machine readable medium of claim 4, wherein:
the multi-tenant services are to be implemented via one or more neural networks, one or more inference resources, neural processing, and/or tensor processing to be implemented using the GPU resource circuitry of the network switch.

### Claim 6 (depends on 5)

The at least one non-transitory machine readable medium of claim 5, wherein:
the respective of the multiple tenants are associated with respective service agreements to be implemented, at least in part, using the network switch;
the respective service agreements are associated with the multi-tenant services; and
the respective tenant identification data is configurable to be associated with respective tenant billing data to be generated based upon providing of the multi-tenant services to the respective of the multiple tenants.

### Claim 7

A method to be implemented in association with a network switch, the network switch being configurable to comprise graphics processing unit (GPU) resource circuitry, data traffic processing circuitry, and management data processing circuitry, the network switch to be used in association with multiple tenants, the method comprising:
receiving, at the network switch, management data and tenant service-related data, the tenant service-related data being configurable to correspond, at least in part, to artificial intelligence (AI) service requests of the multiple tenants, respective portions of the tenant service-related data being associated with respective of the multiple tenants;
generating, by the management data processing circuitry, configuration data, the configuration data to be based upon the management data, the configuration data to configure the GPU resource circuitry of the network switch to implement multi-tenant services associated with the respective of the multiple tenants, the multi-tenant services to be accessed by the respective of the multiple tenants based upon the respective portions of the tenant service-related data; and
routing, by the data traffic processing circuitry, the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch so as to permit the respective of the multiple tenants to access, based upon the respective portions of the tenant service-related data, the multi-tenant services associated with the respective of the multiple tenants;
wherein:
the data traffic processing circuitry is configurable to implement load balancing in association with the routing of the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch;
the multiple tenants are to be associated with respective tenant identification data; and
the data traffic processing circuitry is configurable to implement the routing of the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch based upon priority data.

### Claim 8 (depends on 7)

The method of claim 7, wherein:
the network switch is to be comprised in a cloud-based network.

### Claim 9 (depends on 8)

The method of claim 8, wherein:
the data traffic processing circuitry and/or the management data processing circuitry comprise central processing unit (CPU) core circuitry.

### Claim 10 (depends on 9)

The method of claim 9, wherein:
the GPU resource circuitry of the network switch comprises multiple GPU processing cores.

### Claim 11 (depends on 10)

The method of claim 10, wherein:
the multi-tenant services are to be implemented via one or more neural networks, one or more inference resources, neural processing, and/or tensor processing to be implemented using the GPU resource circuitry of the network switch.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
the respective of the multiple tenants are associated with respective service agreements to be implemented, at least in part, using the network switch;
the respective service agreements are associated with the multi-tenant services; and
the respective tenant identification data is configurable to be associated with respective tenant billing data to be generated based upon providing of the multi-tenant services to the respective of the multiple tenants.

### Claim 13

Circuitry to implement a network switch, the network switch being configurable to comprise graphics processing unit (GPU) resource circuitry, the network switch to be used in association with multiple tenants, the circuitry to implement the network switch comprising:
circuitry to receive, at the network switch, management data and tenant service-related data, the tenant service-related data being configurable to correspond, at least in part, to artificial intelligence (AI) service requests of the multiple tenants, respective portions of the tenant service-related data being associated with respective of the multiple tenants;
management data processing circuitry to generate, based upon the management data, configuration data, the configuration data to configure the GPU resource circuitry of the network switch to implement multi-tenant services associated with the respective of the multiple tenants, the multi-tenant services to be accessed by the respective of the multiple tenants based upon the respective portions of the tenant service-related data; and
data traffic processing circuitry to route the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch so as to permit the respective of the multiple tenants to access, based upon the respective portions of the tenant service-related data, the multi-tenant services associated with the respective of the multiple tenants;
wherein:
the data traffic processing circuitry is configurable to implement load balancing in association with the routing of the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch;
the multiple tenants are to be associated with respective tenant identification data; and
the data traffic processing circuitry is configurable to implement the routing of the respective portions of the tenant service-related data to the GPU resource circuitry of the network switch based upon priority data.

### Claim 14 (depends on 13)

The circuitry to implement the network switch of claim 13, wherein:
the network switch is to be comprised in a cloud-based network.

### Claim 15 (depends on 14)

The circuitry to implement the network switch of claim 14, wherein:
the data traffic processing circuitry and/or the management data processing circuitry comprise central processing unit (CPU) core circuitry.

### Claim 16 (depends on 15)

The circuitry to implement the network switch of claim 15, wherein:
the GPU resource circuitry of the network switch comprises multiple GPU processing cores.

### Claim 17 (depends on 16)

The circuitry to implement the network switch of claim 16, wherein:
the multi-tenant services are to be implemented via one or more neural networks, one or more inference resources, neural processing, and/or tensor processing to be implemented using the GPU resource circuitry of the network switch.

### Claim 18 (depends on 17)

The circuitry to implement the network switch of claim 17, wherein:
the respective of the multiple tenants are associated with respective service agreements to be implemented, at least in part, using the network switch;
the respective service agreements are associated with the multi-tenant services; and
the respective tenant identification data is configurable to be associated with respective tenant billing data to be generated based upon providing of the multi-tenant services to the respective of the multiple tenants.

### Claim 19

A cloud-based networked system to be used in association with multiple tenants, the cloud-based networked system comprising:
compute resources; and
network switch circuitry to be communicatively coupled to the compute resources, the network switch circuitry comprising:
graphics processing unit (GPU) resource circuitry;
circuitry to receive management data and tenant service-related data, the tenant service-related data being configurable to correspond, at least in part, to artificial intelligence (AI) service requests of the multiple tenants, respective portions of the tenant service-related data being associated with respective of the multiple tenants;
management data processing circuitry to generate, based upon the management data, configuration data, the configuration data to configure the GPU resource circuitry to implement, at least in part, multi-tenant services associated with the respective of the multiple tenants, the multi-tenant services to be accessed by the respective of the multiple tenants based upon the respective portions of the tenant service-related data; and
data traffic processing circuitry to route the respective portions of the tenant service-related data to the GPU resource circuitry and to the compute resources so as to permit the respective of the multiple tenants to access, based upon the respective portions of the tenant service-related data, the multi-tenant services associated with the respective of the multiple tenants;
wherein:
the data traffic processing circuitry is configurable to implement load balancing in association with the routing of the respective portions of the tenant service-related data to the GPU resource circuitry and to the compute resources;
the multiple tenants are to be associated with respective tenant identification data; and
the data traffic processing circuitry is configurable to implement the routing of the respective portions of the tenant service-related data based upon priority data.

### Claim 20 (depends on 19)

The cloud-based networked system of claim 19, wherein:
the data traffic processing circuitry and/or the management data processing circuitry comprise central processing unit (CPU) core circuitry.

### Claim 21 (depends on 20)

The cloud-based networked system of claim 20, wherein:
the GPU resource circuitry comprises multiple GPU processing cores.

### Claim 22 (depends on 21)

The cloud-based networked system of claim 21, wherein:
the multi-tenant services are to be implemented via one or more neural networks, one or more inference resources, neural processing, and/or tensor processing to be implemented using the GPU resource circuitry and/or the compute resources.

### Claim 23 (depends on 22)

The cloud-based networked system of claim 22, wherein:
the respective of the multiple tenants are associated with respective service agreements to be implemented, at least in part, using the cloud-based networked system;
the respective service agreements are associated with the multi-tenant services; and
the respective tenant identification data is configurable to be associated with respective tenant billing data to be generated based upon providing of the multi-tenant services to the respective of the multiple tenants.
