Kernel-Smith:一种统一的进化核优化配方
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
AI总结:
Kernel-Smith结合稳定评估驱动的进化代理与进化导向的后训练配方,通过GPU核与运算符生成实现高性能优化,其在KernelBench上取得最佳速度提升,超越多个前沿模型。
摘要:
我们提出了Kernel-Smith,一种高性能GPU核和运算符生成框架,结合稳定评估驱动的进化代理与进化导向的后训练配方。在代理侧,Kernel-Smith维护可执行候选体群体,并通过保存表现优异且多样的程序以及结构化执行反馈进行迭代改进。为使搜索可靠,我们为NVIDIA Triton和MetaX GPUs构建了后端特定的评估服务。在训练侧,我们通过保留正确性保持的高增益修订,将长周期进化轨迹转换为步骤导向的监督和强化学习信号,使模型在进化循环中作为强局部改进者进行优化,而非单次生成器。在统一的进化协议下,Kernel-Smith-235B-RL在KernelBench上取得最佳整体性能,达到最佳平均速度提升率,并超越Gemini-3.0-pro和Claude-4.6-opus等前沿专有模型。我们进一步在MetaX MACA后端验证了该框架,其中Kernel-Smith-MACA-30B超越了DeepSeek-V3.2和Qwen3-235B-2507等大规模模型,展示了在异构平台上的适应潜力。除了基准结果,相同的工作流程还为生产系统如SGLang和LMDeploy贡献了上游成果,证明LLM驱动的核优化可从受控评估转移到实际部署。
英文摘要:
We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe. On the agent side, Kernel-Smith maintains a population of executable candidates and iteratively improves them using an archive of top-performing and diverse programs together with structured execution feedback on compilation, correctness, and speedup. To make this search reliable, we build backend-specific evaluation services for Triton on NVIDIA GPUs and Maca on MetaX GPUs. On the training side, we convert long-horizon evolution trajectories into step-centric supervision and reinforcement learning signals by retaining correctness-preserving, high-gain revisions, so that the model is optimized as a strong local improver inside the evolutionary loop rather than as a one-shot generator. Under a unified evolutionary protocol, Kernel-Smith-235B-RL achieves state-of-the-art overall performance on KernelBench with Nvidia Triton backend, attaining the best average speedup ratio and outperforming frontier proprietary models including Gemini-3.0-pro and Claude-4.6-opus. We further validate the framework on the MetaX MACA backend, where our Kernel-Smith-MACA-30B surpasses large-scale counterparts such as DeepSeek-V3.2-think and Qwen3-235B-2507-think, highlighting potential for seamless adaptation across heterogeneous platforms. Beyond benchmark results, the same workflow produces upstream contributions to production systems including SGLang and LMDeploy, demonstrating that LLM-driven kernel optimization can transfer from controlled evaluation to practical deployment.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。