A message broker where fair scheduling and per-key throttling are first-class primitives.
Tenant-fair LLM inference orchestration on a single GPU. No Kubernetes.
QoS admission control and capacity intelligence for finite AI inference capacity
Per tenant fairness under one shared ceiling with borrowing that never starves a returning tenant
Distributed job scheduling API with priority-based fair-share scheduling, JWT authentication, and resource management. Built with Go, PostgreSQL, and Gin.
Infer and enforce QoS policies for cloud-native workloads using eBPF, ensuring performance and reliability without sidecars.
Fair weekly shift roster generator from CSV inputs (skills, availability, hour caps)
Fairly schedule async tasks and prevent any since user/subject from monopolizing the system resources.
One noisy tenant shouldn't take everyone's GPUs down. A self-hostable LLM gateway that shares inference capacity fairly across tenants, sheds overload cleanly and fails over without breaking an answer.
A TypeScript CLI to fairly schedule team members on Sundays and Wednesdays
A Go-based request queue and gateway for self-hosted LLM inference with admission control, fair scheduling, rate limiting, deduplication, worker leases, and recovery.
To associate your repository with the fair-scheduling topic, visit your repo's landing page and select "manage topics."