Hacker News new | ask | show | jobs
Show HN: Piqc – An open-source GPU waste scanner for LLM inference clusters (github.com)
1 points by samhoss93 14 days ago
1 comments

piqc scans your Kubernetes cluster (Read-only) and identifies which models are running on the wrong GPU tier and what the cost attribution is. It runs in a minute. I'd like to hear the community's experiences/thoughts on our detection approach and its benefits.