no code implementations • 29 Jan 2024 • Shivanshu Shekhar, Tanishq Dubey, Koyel Mukherjee, Apoorv Saxena, Atharv Tyagi, Nishanth Kotla
In this work, we propose optimizing the usage costs of LLMs by estimating their output quality (without actually invoking the LLMs), and then solving an optimization routine for the LLM selection to either keep costs under a budget, or minimize the costs, in a quality and latency aware manner.