METHOD AND SYSTEM FOR DEPLOYMENT OF LARGE LANGUAGE MODELS (LLM) IN CLOUD INSTANCES
Summary
Tata Consultancy Services Limited filed USPTO patent application US20260099706A1 for a method and system to deploy LLMs in cloud instances. The system evaluates cloud instance feasibility based on LLM model size and available storage, determines latency values for batch sizes across LLM-accelerator pairs, and generates deployment recommendations based on latency, cost, workload, application type, and performance metrics.
What changed
Tata Consultancy Services Limited filed USPTO patent application US20260099706A1 for a method and system enabling LLM deployment across multiple cloud instances. The system evaluates feasibility of cloud instances for hosting LLMs based on model size and storage capacity, determines latency values for batch sizes across LLM-accelerator pairs using performance modeling, and generates recommendations based on latency, deployment cost, user workload, application type, latency constraints, and evaluated performance.
Technology companies deploying or developing LLM infrastructure may benefit from reviewing this patent's approach to cloud instance selection and optimization. The patent describes methods for evaluating cost-performance tradeoffs when hosting large language models across distributed cloud environments.
What to do next
- Monitor for updates
Archived snapshot
Apr 15, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
METHOD AND SYSTEM FOR DEPLOYMENT OF LARGE LANGUAGE MODELS (LLM) IN CLOUD INSTANCES
Application US20260099706A1 Kind: A1 Apr 09, 2026
Assignee
Tata Consultancy Services Limited
Inventors
Ashwin KRISHNAN, Venkatesh PASUMARTI, Samarth Sudarshan INAMDAR, Arghyajoy MONDAL, Manoj Karunakaran NAMBIAR, Rekha SINGHAL
Abstract
Existing model deployment approaches have the disadvantage that they do not consider feasibility of cloud instances for hosting a given LLM model. Embodiments disclosed herein provide a method and system for deployment of LLMs in a plurality of cloud instances. The system checks feasibility of the plurality of cloud instances for hosting an LLM, based on size of the LLM and storage space in each of the cloud instances. Further, a latency value for a plurality of batch sizes is determined for a plurality of LLM-accelerator pairs, in each of the plurality of cloud instances identified as feasible based on the feasibility check, using a performance model. Furthermore, a recommendation of one of the plurality of cloud instances identified as feasible is generated, based on the determined latency, a measured cost of deployment, a user workload, an application type, a plurality of latency constraints, and an evaluated performance.
CPC Classifications
G06N 3/08
Filing Date
2025-09-15
Application No.
19328296
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.