2 papers
cs.LG2026
LiteCoOp: Lightweight Multi-LLM Shared-Tree Reasoning for Model-Serving Compiler Optimizations
Annabelle Sujun Tang, Christopher Priebe, Lianhui Qin +1
LLM-guided compiler optimization has recently shown promise, but existing approaches rely on a single large LLM throughout search, making them expensive and excluding smaller model…
cs.LG2026
REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
Annabelle Sujun Tang, Christopher Priebe, Rohan Mahapatra +2
While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid…