3 projects
piqc
Open-source vLLM-native fact collector for AI/ML inference fleets on Kubernetes — detects GPU waste, idle capacity, and tier misplacement
paralleliq-dstack-plugin
dstack plugin that surfaces piqc GPU waste scanning when a GPU fleet or run is applied
paralleliq-skypilot-plugin
SkyPilot AdminPolicy that surfaces piqc GPU waste scanning when a GPU workload is launched on Kubernetes
