This work introduces Calculon-MoE, a tool that jointly explores FLOPS, HBM bandwidth and capacity, multiple network topologies, and popular parallelism/optimization strategies used in LLMs, and quantifies the benefits of overlapping compute and communication, hardware-accelerated collectives, widening the scale-up domain, and higher memory bandwidth and capacity.
Jesmin Jahan Tithi, Hanjiang Wu, Joongun Park et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.