Scalable LLM Reasoning Acceleration with Low-rank Distillation

Harry Dong, Bilge Acun, Beidi Chen, Yuejie Chi

Keywords: large language model, efficiency, distillation, reasoning, scaling, low-rank, inference

TL;DR: We propose an efficient inference algorithm that preserves language and reasoning capabilities and is compatible with many existing efficient algorithms.

Abstract: Due to long generations, large language model (LLM) math reasoning demands significant computational resources and time. While many existing efficient inference methods have been developed with excellent performance preservation on language tasks, they often severely degrade math performance. In this paper, we propose Caprese, a resource-efficient distillation method to recover lost capabilities from deploying efficient inference methods, focused primarily in feedforward blocks. With original weights unperturbed, roughly 1\% of additional parameters, and only 20K synthetic training samples, we are able to recover much if not all of the reasoning capabilities lost from efficient inference for thinking LLMs and without harm to language tasks for instruct LLMs. Moreover, Caprese slashes the number of active parameters ($\sim$2B cut for Gemma 2 9B and Llama 3.1 8B) and integrates cleanly into existing model layers to reduce latency (>16\% time-to-next-token reduction) while encouraging response brevity (up to 8.5\% fewer tokens).

Submission Number: 71