Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
It addresses the problem of scarce expertise for LLM optimization in enterprises, enabling non-expert teams to deploy models efficiently, though it is incremental as it builds on existing optimization techniques.
The paper tackles the challenge of scaling enterprise LLM deployment within compute constraints by automating optimization workflows, resulting in more than 2x GPU throughput improvement in production.
Enterprise LLM deployment faces a critical scalability challenge: organizations must optimize models systematically to scale AI initiatives within constrained compute budgets, yet the specialized expertise required for manual optimization remains a niche and scarce skillset. This challenge is particularly evident in managing GPU utilization across heterogeneous infrastructure while enabling teams with diverse workloads and limited LLM optimization experience to deploy models efficiently. We present OptiKIT, a distributed LLM optimization framework that democratizes model compression and tuning by automating complex optimization workflows for non-expert teams. OptiKIT provides dynamic resource allocation, staged pipeline execution with automatic cleanup, and seamless enterprise integration. In production, it delivers more than 2x GPU throughput improvement while empowering application teams to achieve consistent performance improvements without deep LLM optimization expertise. We share both the platform design and key engineering insights into resource allocation algorithms, pipeline orchestration, and integration patterns that enable large-scale, production-grade democratization of model optimization. Finally, we open-source the system to enable external contributions and broader reproducibility.