Nvidia patents data translator for AI model pipelines
Nvidia describes a software adaptor that sits between data sources and AI models to manage how information flows. It reads details about the specific AI model being used and automatically converts incoming data into the exact format that model needs to process it correctly.
In the filing’s own words
The present disclosure provides an adaptor for managing data flow in an inference pipeline. The adaptor comprises a non-transitory memory device storing instruction code modules and at least one processor configured to execute the modules. The processor is configured to collect model metadata describing at least one machine-learning (ML) based inference model deployed within the inference pipeline, define a required ingress data format for interfacing the inference model based on the model metadata, employ an ingress adaptation module to receive an input data element from one or more data input sources and translate the input data element according to the ingress data format, and process the translated input data element through the inference model to generate at least one first inference result.
What exactly they claim (claim 1)
1. An adaptor for managing data flow in an inference pipeline, the adaptor operationally connected to a non-transitory memory device, wherein modules of instruction code are stored, and comprising at least one processor associated with the memory device, and configured to execute the modules of instruction code, whereupon execution of said modules of instruction code, the at least one processor is configured to: collect model metadata, describing at least one machine-learning (ML) based inference model, deployed within the inference pipeline; based on the model metadata, defining a required ingress data format for interfacing the at least one inference model; employ an ingress adaptation module, to receive an input data element from one or more data input sources, and translate said input data element according to the ingress data format; and process the translated input data element through the at least one inference model, to generate at least one first inference result.
Facts
- Company
- Nvidia (Nvidia Corporation)
- Official title
- ADAPTOR FOR MANAGING DATA FLOW IN AN INFERENCE PIPELINE, AND METHOD OF USING THEREOF
- Publication number
- US20260320433A1
- Application number
- 19177789
- Filed
- Apr 14, 2025
- Published
- Oct 15, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06N 5/04 Physics & computingH04L 49/3063 Electricity & electronicsMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.