Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

• URL: http://arxiv.org/abs/2603.28342v1
• Date: Mon, 30 Mar 2026 12:12:49 GMT
• Title: Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
• Abstract summary: Kernel-Smith is a framework for high-performance GPU kernel and operator generation.<n>On the agent side, Kernel-Smith maintains a population of executable candidates and iteratively improves them.<n>On the training side, we convert long-horizon evolution trajectories into step-centric supervision and reinforcement learning signals.
• Score: 48.656549870801285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts [29.878782850560132]
  Kernel Foundry is a diagnosis-driven evolutionary framework for automatic GPU kernel optimization.<n> Experiments on KernelBench show that our method consistently improves both correctness and performance over strong baselines.
  arXiv  Detail & Related papers  (2026-05-08T03:41:54Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• KernelFoundry: Hardware-aware evolutionary GPU kernel optimization [9.20884368317651]
  KernelFoundry is an evolutionary framework that efficiently explores the GPU kernel design space.<n>We evaluate this framework on KernelBench, robust-kbench, and custom tasks.<n>Our approach consistently outperforms the baseline methods, achieving an average speed of 2.3x on KernelBench for SYCL.
  arXiv  Detail & Related papers  (2026-03-12T20:40:04Z)
• Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis [68.7701048879757]
  EvoKernel is a self-evolving agentic framework that automates the lifecycle of kernel synthesis.<n>It learns stage-specific Q-values that prioritize experiences based on their contribution to the current objective.<n>It improves models' correctness from 11.0% to 83.0% and a median speedup of 3.60x over initial drafts.
  arXiv  Detail & Related papers  (2026-03-11T14:57:06Z)
• CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation [51.72529978689561]
  Agent is a large-scale agentic reinforcement learning system that develops kernel expertise through three components.<n>Agent delivers 100%, 100%, and 92% faster rate over torchcompile on KernelBench.
  arXiv  Detail & Related papers  (2026-02-27T18:58:05Z)
• K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model [57.440609834690385]
  Existing approaches treat Large Language Models (LLMs) as rapid code generators within evolutionary loops.<n>We propose Search via Co-Evolving World Model and build K-Search based on this method.<n>We evaluate K-Search on diverse, complex kernels FlashInfer, including GQA, MLA, and MoE kernels.
  arXiv  Detail & Related papers  (2026-02-22T11:06:22Z)
• KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta [8.852510847427164]
  This paper presents KernelEvolve-an agentic kernel coding framework to tackle heterogeneous at-scale for deep learning recommendation model (DLRM)<n> KernelEvolve is designed to take kernel specifications as input and automate the process of kernel generation and optimization for recommendation model across heterogeneous hardware architectures.<n>We show KernelEvolve reduces development time from weeks to hours and substantial performance improvements over PyTorch baselines across diverse production use cases and for heterogeneous AI systems at-scale.
  arXiv  Detail & Related papers  (2025-12-29T06:31:55Z)
• cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution [15.701861287574296]
  cuPilot is a strategy-coordinated multi-agent framework that introduces strategy as an intermediate semantic representation for kernel evolution.<n>On the GEMM tasks, cuPilot showcases sophisticated optimizations and achieves high utilization of critical hardware units.
  arXiv  Detail & Related papers  (2025-12-18T12:34:00Z)
• PRAGMA: A Profiling-Reasoned Multi-Agent Framework for Automatic Kernel Optimization [12.24680414520151]
  PRAGMA is a profile-guided AI kernel generation framework.<n>It integrates execution feedback and fine-grained hardware profiling into the reasoning loop.<n>We evaluate PRAGMA on KernelBench, covering GPU and CPU backends.
  arXiv  Detail & Related papers  (2025-11-09T12:01:43Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives [55.79741270235602]
  We develop a hybrid solution to the development of deep learning kernels. We use the advanced polyhedral technology to automatically tune the outer loops for performance.
  arXiv  Detail & Related papers  (2020-02-06T08:02:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.