|
Work item:
|
F.AICP-IO
|
|
Subject/title:
|
Technical specification for artificial intelligence cloud platform: Inference optimization
|
|
Status:
|
Under study
|
|
Approval process:
|
AAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2027 (Medium priority)
|
|
Liaison:
|
ITU-T SG13, SG17
|
|
Supporting members:
|
Beijing Baidu Netcom Science Technology Co., Ltd., China Mobile Communications Co. Ltd., China Telecommunications Corporation, China Unicom, Huawei Technologies Co., Ltd., Alibaba China Co. Ltd., Hangzhou Hikvision Digital Technology Co.,Ltd., Tencent Technology (Shenzhen) Company Limited
|
|
Summary:
|
This draft recommendation provides technical requirements includes resource support, data processing, model processing, model deployment, model inference, and service construction, and from the perspective of the cloud-edge-end dimension, specific capability requirements are put forward around functionality, performance, and stability. The purpose of this draft recommendation is to build an advanced platform architecture that meets the needs of foundation model inference optimization and promotes the in-depth application and development of foundation models in various industries. It is submitted for discussion and approval at the Q5/21 meeting.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2025-02-25 14:37:36
|
|
Last update:
2025-02-25 14:46:55
|
|
