22:53
2026-08-03
arxiv.org
artificial-intelligence
Compiler-Grounded Hierarchical Diagnosis for LLM Triton Kernel Optimization
Researchers have developed a compiler-grounded hierarchical optimization framework for Triton kernels that achieves a geometric-mean speedup of 4.35ร and a median speedup of 2.73ร across 37 benchmark โฆ