Blog
Practical writing on Kubernetes, observability, migrations, platform engineering, and production infrastructure.
- Types of LLM Explained: Dense, MoE, and Everything In Between
- LLM Inference KPIs Every SRE Should Know
- Kubernetes Gateway API Inference Extension
- NVIDIA DSX
- ndots in Kubernetes
- Celery to Argo Workflows
- Scaling Prometheus with Thanos
- 100 TB from InfluxDB to Grafana Mimir
- Overview of gRPC
- Monitoring with Prometheus
- Streamlining Model Lifecycle with KubeRay
- Making Kubernetes Simple with Talos