Recommended model architecture/parameter settings to emulate real-world workload?

Many thanks for the great work!

1) Recommendation system is a very import application in AI. I was wondering if there is set of recommended settings (e.g. the scales of data, embedding table sizes, feature interaction architecture etc.) to emulate a production-level recsys inference/training, so we can understand what the exact workload is like?

2) Besides, what sort of hardware are best suited for inference or training, CPUs and/or GPUs? I'm very curious what each component in a recsys is like, which part is memory/compute/communication bound? What parallelizing methods (TP, DP, mixed butterfly etc) are employed?

3) Additionally, if a recsys is combined with LLMs (or it is LLM architecture), how do they interact, does RecIS support it?

Kind regards

The issue names no files, tests, or entry points to investigate. It asks for production recommendation-system configurations, hardware and parallelization guidance, and possible LLM integration, so a contributor would first need to define the supported scope and success criteria with maintainers.

Written by the indexing model from the issue text.