Reproduce “AIBench: An Industry Standard Internet Service AI Benchmark Suite” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Wanling Gao, Fei Tang, Lei Wang, Jianfeng Zhan, Chunxin Lan, Chunjie Luo, Yunyou Huang, Chen Zheng and 17 more
AIBench benchmarks AI in Internet services by combining end-to-end request paths with reusable component and microbenchmarks. It supports online inference, offline training, and deployment across 16 AI domains. In an e-commerce search prototype, full-path latency reached 956 ms at the 99th percentile, with the recommender slowest; this baseline is not production performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.