Dell Products Inc.

Balasubramanian Chandrasekaran

Dharmesh M Patel

John Kelly

Lucas A Wilson

Timothy E Abels

A method for managing selection of an inferencing workload placement based on security considerations includes obtaining, by a variant selection agent of a workload placement service and from a front-end device, a request for an inferencing payload associated with an inferencing workload implementing a generative artificial intelligence (AI) model, and in response to the request: performing a payload classification on the request to determine a variant selection for the inferencing workload, making a determination that the variant selection is a secured variant, in response to the determination, transmitting the request to the secured variant, wherein the secured variant executes an instance of the inferencing workload on a secured production environment, obtaining, from the secured variant, the inferencing payload, and providing the inferencing payload to the front-end device.

Security-based artificial intelligence workload allocation in a heterogeneous environment

A system for managing of a security based inferencing workload placement includes a security a variant selection agent, production environments, and a front-end device that includes a security variant initial agent. The security variant initial agent is programmed to: obtain a request for an inferencing payload for an artificial intelligence (AI) model, wherein the request comprises a prompt for the AI model generated by the user, in response to the request: perform an initial classification analysis on the request to obtain a classification-eligible tag for the request, make a first determination, based on the classification-eligible tag, that the request is classification-eligible, based on the first determination, transmit the request to the workload placement service for a variant selection operation.

Front-end environment enforcement of security-based artificial intelligence workload allocation

Methods and systems for providing computer implemented services using pods are disclosed. To provide the computer implemented services, instances of the pods may be deployed to data processing systems. When a new instance of a pod is created, a volume for the pod may be established. To select where to create instances of pods, locations where data access conflicts are less likely to arise may be selected. These locations may be identified based on the locations of pods and data access patterns for the pods.

System and method for managing data access in distributed systems

A model lifecycle management method includes: executing a model initial development phase based on at least a first criteria, a second criteria, and a third criteria to obtain a set of production ready models; executing, using the set of production ready models, a model production phase based on at least a fourth criteria, a fifth criteria, and a sixth criteria to obtain; and executing, after executing the model production phase, using the set of models to be updated, a model update phase based on at least a seventh criteria on at least one model in the model production phase.

Systems and methods for model lifecycle management

A storage services device includes: a first processor that provides first server services for a server having a second processor that is coupled to a second storage and that provides second server services of the server and a storage controller coupled to a first storage of the server that transmits information about the first storage to the first processor. The storage services device is disposed in the server and disaggregates, within the server, the first server services from the second server services.

Smart storage services device

A method and system for optimizing a learning model post-deployment. Specifically, the disclosed method and system re-optimize&#x2014;i.e., re-train and/or re-validate&#x2014;machine learning and/or artificial intelligence algorithms that have already been deployed into a production environment. During post-deployment, the re-optimization process may transpire following the advent of varying model re-adjustment triggers.

Method and system for optimizing learning models post-deployment

A system and method for hot cloning in a distributed network is disclosed. In one embodiment, a method for cloning a virtual machine from a source system to a target system includes freezing writes to a storage file having storage blocks such that subsequent writes create new storage blocks for the original virtual machine. The method further including freezing writes to a memory content such that subsequent writes store in buffers. The method further including copying the memory content onto the target system wherein the copied memory content creates a clone. The method further including unfreezing the memory content by merging the writes stored in the buffers and unfreezing the writes to the storage file such that subsequent writes take place normally. The method further including configuring the clone based on the target system. The method further including creating a new storage block for any writes to the storage file whereby the new storage block is not shared.

Growing community of inventors

Austin, TX, United States of America

Balasubramanian Chandrasekaran