The AI development interface, AI model interoperable representation, coding format, and model encapsulated format for efficient AI model inference, storage, distribution, and management are discussed in this standard.
- Standard Committee
- C/DC - Data Compression Standards Committee
- Status
- Active Standard
- PAR Approval
- 2020-09-24
- Board Approval
- 2021-12-08
- History
-
- Published:
- 2022-03-18
Working Group Details
- Society
- IEEE Computer Society
- Standard Committee
- C/DC - Data Compression Standards Committee
- Working Group
-
AIM - AI Model Representation, Compression, Distribution and Management
- IEEE Program Manager
- Meng Zhao
Contact Meng Zhao - Working Group Chair
- Yonghong Tian
Other Activities From This Working Group
Current projects that have been authorized by the IEEE SA Standards Board to develop a standard.
P2941.3
Standard for Representation and Application Programming Interface (API) of Large-scale Pre-trained Artificial Intelligence (AI) Models
The standard provides a representation and API framework for large-scale pre-trained AI models, including its training, inference, transfer, mixture, instruct-tuning, representation, compression, distribution, and services. This standard aims to facilitate the development and deployment of large-scale pre-trained AI models across different platforms and domains.
Standards approved by the IEEE SA Standards Board that are within the 10-year lifecycle.
2941.1-2022
IEEE Standard for Operator Interfaces of Artificial Intelligence
A set of operator interfaces frequently used in artificial intelligence (AI) applications is defined in this standard, where the AI operators refer to the standard building blocks and primitives for performing basic AI operations. The functionality and the specific input and output operands of an AI operator are discussed, as well as both generality and efficiency. Various types of operators, such as those related to basic mathematics, neural network, and machine learning, are highlighted.
2941.2-2023
IEEE Standard for Application Programming Interfaces (APIs) for Deep Learning (DL) Inference Engines
A set of application programming interfaces (APIs) that is aimed at breaking down the barriers between different deep learning (DL) inference engines and applications is defined in this standard. The APIs are comprised of functional interfaces including parameter reading, model compilation optimization, operator registration, thread management, input/output data acquisition, inference instance creation, and inference execution.
These standards have been replaced with a revised version of the standard, or by a compilation of the original active standard and all its existing amendments, corrigenda, and errata.
No Superseded Standards
These standards have been removed from active status through a ballot where the standard is made inactive as a consensus decision of a balloting group.
No Inactive-Withdrawn Standards
These standards are removed from active status through an administrative process for standards that have not undergone a revision process within 10 years.
No Inactive-Reserved Standards