CAKE lets GPU kernel agents program compilers directly, boosting Flash‑KMeans speed
CAKE is a compiler‑agent co‑design framework that gives GPU agents a typed, hardware‑explicit IR (CAKE IR) exposing warp roles, memory movement and pipelines, enabling verification and cost modeling. On NVIDIA Ampere–Blackwell GPUs it outperforms tuned FlashML by 1.14× on Flash‑KMeans and delivers a 2.05× speedup on Kimi Delta Attention, with four kernel changes already merged upstream.