The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Mar. 24, 2026
Filed:
Oct. 27, 2022
Load testing and performance benchmarking for large language models using a cloud computing platform
Microsoft Technology Licensing, Llc, Redmond, WA (US);
Sanjay Ramanujan, Bellevue, WA (US);
Rakesh Kelkar, Bellevue, WA (US);
Hari Krishnan Srinivasan, Bellevue, WA (US);
Karthik Raman, Sammamish, WA (US);
Hema Vishnu Pola, Hyderabad, IN;
Sagar Taneja, Ghaziabad, IN;
Mradul Karmodiya, Madya Pradesh, IN;
MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US);
Abstract
The techniques disclosed herein enable systems to perform repeatable and iterative load testing and performance benchmarking for artificial intelligence models deployed in a cloud computing environment. This is achieved by utilizing load profiles and representative workloads generated based on the load profiles to evaluate an artificial intelligence model under various workload contexts. The representative workload is then executed by the artificial intelligence model utilizing available computing infrastructure. Performance metrics are extracted from the execution and analyzed to provide insight into various performance dynamics such as the relationship between latency and data throughput. In addition, load profiles and input datasets are dynamically adjusted to evaluate different scenarios and use cases enabling the system to automatically test the artificial intelligence model across diverse applications. Furthermore, by comparing various iterations of the artificial intelligence model, a quality gate can be constructed to enforce a consistent and high-quality user experience.