DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation 事件

DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation arXiv:2603.21465v2 Announce Type: replace Abstract: Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Models (LLMs) to automatically convert PyTorch reference implementations to CUDA kernels, significantly reducing engineering effort. State-of-the-art LLMs, such as GPT-5.2 and Claude-Sonnet-4.5, still strugg