{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11520592","patent":{"patent_number":"US-11520592","title":"Executing large artificial intelligence models on memory-constrained devices","assignee":null,"inventors":[],"filing_date":"2019-09-20T00:00:00.000Z","publication_date":"2022-12-06T00:00:00.000Z","cpc_codes":["G06F","G06N","G06F","G06N","G06N","G06N","G06N","H04L","H04L","G06F","G06F"],"num_claims":20,"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."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Executing large artificial intelligence models on memory-constrained devices","description":"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","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11520592","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11520592","citation_suggestion":"Patentable. \"Executing large artificial intelligence models on memory-constrained devices\" (US-11520592). https://patentable.app/patents/US-11520592","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11520592","json":"https://patentable.app/api/llm-context/US-11520592","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T14:08:23.528Z"}