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.

Abstract: Technologies for function as a service (FaaS) arbitration include an edge gateway, multiple endpoint devices, and multiple service providers. The edge gateway receives a registration request from a service provider that is indicative of an FaaS function identifier and a transform function. The edge gateway verifies an attestation received from the service provider and registers the service provider. The edge gateway receives a function execution request from an endpoint device that is indicative of the FaaS function identifier. The edge gateway selects the service provider based on the FaaS function identifier, programs an accelerator with the transform function, executes the transform function with the accelerator to transform the function execution request to a provider request, and submits the provider request to the service provider. The service provider may be selected based on an expected service level included in the function execution request. Other embodiments are described and claimed.

Abstract: An architecture to allow Multi-Access Edge Computing (MEC) billing and charge tracking, is disclosed. In an example, a tracking process, such as is performed by an edge computing apparatus, includes: receiving a computational processing request for a service operated with computing resources of the edge computing apparatus from a connected edge device within the first access network, wherein the computational processing request includes an identification of the connected edge device; identifying a processing device, within the first access network, for performing the computational processing request; and storing the identification of the connected edge device, a processing device identification, and data describing the computational processes completed by the processing device in association with the computational processing request.

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.

Abstract: Systems and techniques for AI model and data camouflaging techniques for cloud edge are described herein. In an example, a neural network transformation system is adapted to receive, from a client, camouflaged input data, the camouflaged input data resulting from application of a first encoding transformation to raw input data. The neural network transformation system may be further adapted to use the camouflaged input data as input to a neural network model, the neural network model created using a training data set created by applying the first encoding transformation on training data. The neural network transformation system may be further adapted to receive a result from the neural network model and transmit output data to the client, the output data based on the result.

Abstract: Examples described herein relate to management of battery-use by one or more computing resources in the event of a power outage. Data used by one or more computing resources can be backed-up using battery power. Battery power is allocated to data back-up operations based at least on one or more of: criticality level of data, priority of an application that processes the data, or priority level of resource. The computing resource can back-up data to a persistent storage media. The computing resource can store a log of data that is backed-up or not backed-up. The log can be used by the computing resource to access the backed-up data for continuing to process the data and to determine what data is not available for processing.

Abstract: A computing cluster can receive a request to perform a workload from a client. The request can include a service discovery agent. If the request is authenticated and permitted on the computing cluster, the service discovery agent is executed. Execution of the service discovery agent can lead to discovery of resource capabilities of the cluster and selection of the appropriate resource based on performance requirements. The selected resource can be deployed for execution of the workload.

Abstract: Various systems and methods for implementing a service-level agreement (SLA) apparatus receive a request from a requester via a network interface of the gateway, the request comprising an inference model identifier that identifies a handler of the request, and a response time indicator. The response time indicator relates to a time within which the request is to be handled indicates an undefined time within which the request is to be handled. The apparatus determines a network location of a handler that is a platform or an inference model to handle the request consistent with the response time indicator, and routes the request to the handler at the network location.

Abstract: Technologies for accelerating edge device workloads at a device edge network include a network computing device which includes a processor platform that includes at least one processor which supports a plurality of non-accelerated function-as-a-service (FaaS) operations and an accelerated platform that includes at least one accelerator which supports a plurality of accelerated FaaS (AFaaS) operation. The network computing device is configured to receive a request to perform a FaaS operation, determine whether the received request indicates that an AFaaS operation is to be performed on the received request, and identify compute requirements for the AFaaS operation to be performed. The network computing device is further configured to select an accelerator platform to perform the identified AFaaS operation and forward the received request to the selected accelerator platform to perform the identified AFaaS operation. Other embodiments are described and claimed.

Abstract: Various systems and methods of initiating and performing contextualized AI inferencing, are described herein. In an example, operations performed with a gateway computing device to invoke an inferencing model include receiving and processing a request for an inferencing operation, selecting an implementation of the inferencing model on a remote service based on a model specification and contextual data from the edge device, and executing the selected implementation of the inferencing model, such that results from the inferencing model are provided back to the edge device. Also in an example, operations performed with an edge computing device to request an inferencing model include collecting contextual data, generating an inferencing request, transmitting the inference request to a gateway device, and receiving and processing the results of execution. Further techniques for implementing a registration of the inference model, and invoking particular variants of an inference model, are also described.

Abstract: Example edge gateway circuitry to schedule service requests in a network computing system includes: gateway-level hardware queue manager circuitry to: parse the service requests based on service parameters in the service requests; and schedule the service requests in a queue based on the service parameters, the service requests received from client devices; and hardware queue manager communication interface circuitry to send ones of the service requests from the queue to rack-level hardware queue manager circuitry in a physical rack, the ones of the service requests corresponding to functions as a service provided by resources in the physical rack.

Abstract: An apparatus for training artificial intelligence (AI) models is presented. In embodiments, the apparatus may include an input interface to receive in real time model training data from one or more sources to train one or more artificial neural networks (ANNs) associated with the one or more sources, each of the one or more sources associated with at least one of the ANNs; a load distributor coupled to the input interface to distribute in real time the model training data for the one or more ANNs to one or more AI appliances; and a resource manager coupled to the load distributor to dynamically assign one or more computing resources on ones of the AI appliances to each of the ANNs in view of amounts of the training data received in real time from the one or more sources for their associated ANNs.

Abstract: Systems and methods may be used to determine where to run a service based on workload-based conditions or system-level conditions. An example method may include determining whether power available to a resource of a compute device satisfies a target power, for example to satisfy a target performance for a workload. When the power available is insufficient, an additional resource may be provided, for example on a remote device from the compute device. The additional resource may be used as a replacement for the resource of the compute device or to augment the resource of the compute device.

Abstract: Technologies for matching security requirements for a function-as-a-service (FaaS) function request to an edge resource having security features matching the security requirements are disclosed. According to one embodiment of the present disclosure, an edge gateway device receives, from an edge device, a request to execute an accelerated function. The edge gateway device selects, as a function of one or more security requirements requested by the edge device, an edge resource to fulfill the request. The edge gateway device transmits the request to the edge resource to fulfill the request of the edge device, according to the one or more security requirements.

Abstract: There is disclosed an example of an artificial intelligence (AI) system, including: a first hardware platform; a fabric interface configured to communicatively couple the first hardware platform to a second hardware platform; a processor hosted on the first hardware platform and programmed to operate on an AI problem; and a first training accelerator, including: an accelerator hardware; a platform inter-chip link (ICL) configured to communicatively couple the first training accelerator to a second training accelerator on the first hardware platform without aid of the processor; a fabric ICL to communicatively couple the first training accelerator to a third training accelerator on a second hardware platform without aid of the processor; and a system decoder configured to operate the fabric ICL and platform ICL to share data of the accelerator hardware between the first training accelerator and second and third training accelerators without aid of the processor.

Abstract: Various systems and methods of initiating and performing contextualized AI inferencing, are described herein. In an example, operations performed with a gateway computing device to invoke an inferencing model include receiving and processing a request for an inferencing operation, selecting an implementation of the inferencing model on a remote service based on a model specification and contextual data from the edge device, and executing the selected implementation of the inferencing model, such that results from the inferencing model are provided back to the edge device. Also in an example, operations performed with an edge computing device to request an inferencing model include collecting contextual data, generating an inferencing request, transmitting the inference request to a gateway device, and receiving and processing the results of execution. Further techniques for implementing a registration of the inference model, and invoking particular variants of an inference model, are also described.

Abstract: There is disclosed an example of an artificial intelligence (AI) system, including: a first hardware platform; a fabric interface configured to communicatively couple the first hardware platform to a second hardware platform; a processor hosted on the first hardware platform and programmed to operate on an AI problem; and a first training accelerator, including: an accelerator hardware; a platform inter-chip link (ICL) configured to communicatively couple the first training accelerator to a second training accelerator on the first hardware platform without aid of the processor; a fabric ICL to communicatively couple the first training accelerator to a third training accelerator on a second hardware platform without aid of the processor; and a system decoder configured to operate the fabric ICL and platform ICL to share data of the accelerator hardware between the first training accelerator and second and third training accelerators without aid of the processor.

Abstract: An architecture to perform resource management among multiple network nodes and associated resources is disclosed. Example resource management techniques include those relating to: proactive reservation of edge computing resources; deadline-driven resource allocation; speculative edge QoS pre-allocation; and automatic QoS migration across edge computing nodes.

Abstract: Various systems and methods for enhancing a distributed computing environment with multiple edge hosts and user devices, including in multi-access edge computing (MEC) network platforms and settings, are described herein. A device of a lifecycle management (LCM) proxy apparatus obtains a request, from a device application, for an application multiple context of an application. The application multiple context for the application is determined. The request from the device application for the application multiple context for the application is authorized. A device application identifier based on the request is added to the application multiple context. A created response for the device application based on the authorization of the request is transmitted to the device application. The response includes an identifier of the application multiple context.

Abstract: Various systems and methods for implementing a service-level agreement (SLA) apparatus receive a request from a requester via a network interface of the gateway, the request comprising an inference model identifier that identifies a handler of the request, and a response time indicator. The response time indicator relates to a time within which the request is to be handled indicates an undefined time within which the request is to be handled. The apparatus determines a network location of a handler that is a platform or an inference model to handle the request consistent with the response time indicator, and routes the request to the handler at the network location.