FeaturedEntry 007

Running LLMs on GKE: what breaks before you find the Inference Gateway

When someone first asks to run an LLM on Kubernetes, the instinct is reasonable: it's a containerised workload, it exposes an HTTP API, it needs to scale. Deploy it like anything else — a `Deployment`, a `Service`, maybe an `HPA` on CPU. That instinct gets you surprisingly far. Until it doesn't

Read Entry

Recent Entries

Chronological archive
No.DateTitleTime
00606/10/2024Platform Engineering: Building the Right Abstractions3 min read
00505/01/2024Data Pipelines on Kubernetes: Lessons from Airflow to Argo3 min read
00403/20/2024Progressive Delivery with Argo Rollouts3 min read
00303/05/2024LLMOps in Production: What Nobody Tells You3 min read
00202/08/2024Writing Production-Grade Kubernetes Operators3 min read
00101/15/2024GitOps at Scale: Managing 50 Clusters with Flux3 min read

The Operations Brief

Weekly deep-dives into systems engineering, platform design, and technical debt management. Directly to your inbox.

Technical Journaling

Lighthouseops is a peer-reviewed engineering log for practitioners. No fluff, just architecture.