Results for “metropolis”

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

Enforces ML infrastructure, experiment tracking, reproducibility, model packaging, CI/CD, monitoring, and infrastructure-as-code standards at principal-engineer level.

Deploy and serve AI/ML models on Modal's serverless cloud platform with on-demand GPUs, autoscaling containers, persistent storage, and scheduled jobs.