~
jonte@melbourne:~/blog$ ls -la --sort=date

Writing

Notes on DevSecOps, AI/LLM tooling, cloud security, and things I've built and learned along the way.

PUBLISHED
3 Articles
TOPICS
12 Tags
VERIFIED
100% Human-Edited
/rss.xml

Showing 3 of 3 posts

Ephemeral GPU Fleet Orchestration for ComfyUI on RunPod diagram
2 min read

Ephemeral GPU Fleet Orchestration for ComfyUI on RunPod

How I built PodBench to parse ComfyUI node graphs into declarative manifests, pre-warm content-addressed safetensors caches, and cut cold-boot GPU provisioning times from 22 minutes to under 90 seconds.

✓ Authored by Jonte de ZwartRead →