Patents by Inventor Gautham Popuri

Gautham Popuri has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Executing large artificial intelligence models on memory-constrained devices
    Patent number: 11520592
    Abstract: Methods, systems, apparatuses, and computer program products are described herein that enable execution of a large AI model on a memory-constrained target device that is communicatively connected to a parameter server, which stores a master copy of the AI model. The AI model may be dissected into smaller portions (e.g., layers or sub-layers), and each portion may be executed as efficiently as possible on the target device. After execution of one portion of the AI model is finished, another portion of the AI model may be downloaded and executed at the target device. To improve efficiency, the input samples may be divided into microbatches, and a plurality of microbatches executing in sequential order may form a minibatch. The size of the group of microbatches or minibatch can be manually or automatically adjusted to reduce the communication overhead.
    Type: Grant
    Filed: September 20, 2019
    Date of Patent: December 6, 2022
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Bharadwaj Pudipeddi, Marc Tremblay, Gautham Popuri, Layali Rashid, Tiyasa Mitra, Mohit Mittal, Maral Mesmakhosroshahi
  • EXECUTING LARGE ARTIFICIAL INTELLIGENCE MODELS ON MEMORY-CONSTRAINED DEVICES
    Publication number: 20220276871
    Abstract: Methods, systems, apparatuses, and computer program products are described herein that enable execution of a large AI model on a memory-constrained target device that is communicatively connected to a parameter server, which stores a master copy of the AI model. The AI model may be dissected into smaller portions (e.g., layers or sub-layers), and each portion may be executed as efficiently as possible on the target device. After execution of one portion of the AI model is finished, another portion of the AI model may be downloaded and executed at the target device. To improve efficiency, the input samples may be divided into microbatches, and a plurality of microbatches executing in sequential order may form a minibatch. The size of the group of microbatches or minibatch can be manually or automatically adjusted to reduce the communication overhead.
    Type: Application
    Filed: May 18, 2022
    Publication date: September 1, 2022
    Inventors: Bharadwaj PUDIPEDDI, Marc TREMBLAY, Gautham POPURI, Layali RASHID, Tiyasa MITRA, Mohit MITTAL, Maral MESMAKHOSROSHAHI
  • EXECUTING LARGE ARTIFICIAL INTELLIGENCE MODELS ON MEMORY-CONSTRAINED DEVICES
    Publication number: 20210019151
    Abstract: Methods, systems, apparatuses, and computer program products are described herein that enable execution of a large AI model on a memory-constrained target device that is communicatively connected to a parameter server, which stores a master copy of the AI model. The AI model may be dissected into smaller portions (e.g., layers or sub-layers), and each portion may be executed as efficiently as possible on the target device. After execution of one portion of the AI model is finished, another portion of the AI model may be downloaded and executed at the target device. To improve efficiency, the input samples may be divided into microbatches, and a plurality of microbatches executing in sequential order may form a minibatch. The size of the group of microbatches or minibatch can be manually or automatically adjusted to reduce the communication overhead.
    Type: Application
    Filed: September 20, 2019
    Publication date: January 21, 2021
    Inventors: Bharadwaj Pudipeddi, Marc Tremblay, Gautham Popuri, Layali Rashid, Tiyasa Mitra, III, Mohit Mittal, Maral Mesmakhosroshahi