Covering 5 mainstream domestic chips, CAICT releases the industry’s first benchmark for evaluating intelligent computing operations and maintenance agents.

robot
Abstract generation in progress
ME AI News: The China Academy of Information and Communications Technology (CAICT) has released version 3.0 of the AISHPerf AI software and hardware benchmarking system. It includes two core evaluation benchmarks in the AI infrastructure domain—AISHPerf Intelligent Computing Operations Agent Benchmark and AISHPerf Operator Generation Agent Benchmark. These two benchmarks were co-built with major technical support from the domestic AI-native infrastructure service provider Wuwen Qiong and a team from Tsinghua University. The AISHPerf Intelligent Computing Operations Agent Benchmark is the first among similar benchmarking systems to include specific scenarios and typical issue test cases for the operation and maintenance of five types of domestic chip clusters—Tianshu, Biren, Muxi, Moore, and Ascend—thereby, for the first time, establishing a unified, quantifiable evaluation yardstick for domestic intelligent computing operations agents and filling a standards gap in the domestic intelligent computing operations field. (Science and Technology Innovation Board Daily) (Source: Eastmoney)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned