cs.AINov 14, 2026

CompoundingKernel: Self-Improving from Zero to First

Authors: Qian Qu, Hongyang Wang, Wenbo Chen, Yichuan Li, Jingguo Liu, Xian Li, Xuan Wang, Ruochen Wen, 

Abstract

We present CompoundingKernel, a self-improving agent system that writes GPU kernels by search. As of 2026-11-11, its generated kernels rank #1 on the public L1, L2 and Quantization boards of SOL-ExecBench (NVIDIA B200). They have held #1 on L1 since 2026-10-27, albeit a short loss on 2026-11-07. All 235 problems have a site-verified correct kernel; on the 209 public-board problems they are 4.40x faster than the benchmark's reference baseline. The search starts from zero: agents get each problem's PyTorch definition but no reference kernels or official scores. A per-problem archive outside the model holds every correct kernel and its lineage. An LLM controller reads it, picks a parent or a new design, and gives each parallel child agent one direction. Checks outside the model decide correctness. At equal wall time, it beat a coded UCB style tree on 35 of 38 problems by making 2.4x as many correct attempts. Over a thousand agents ran at once, and one warm restart fix raised their evaluation rate 3.6x. We find that the rate of reliable measurements, not the number of agents, limits how far such a search scales. Our code and kernels are available on URL.

Figures & tables

Explore similar work

May 22, 2026

FastKernels: Benchmarking GPU Kernel Generation in Production

LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize against. Existing benchmarks are poorly aligned with production inference frameworks: they evaluate kernels on a single GPU with synthetic inputs, ignore the surrounding compilation stack, and reward replicating known optimizations rather than discovering new ones. The resulting reward signals are misleading: agents learn to generate kernels that score well in sandboxes but introduce interface incompatibilities, compilation-stack conflicts, and silent correctness degradation when integrated into real systems. We introduce FastKernels, a kernel benchmark built around a minimal set of 46 representative architectures spanning 8 categories, whose kernels collectively subsume those of 96.2% (409/425) of HuggingFace Transformers architectures. FastKernels doubles as a minimalistic, production-grade inference framework that runs at parity with hardened systems such as vLLM and SGLang on mainstream LLM serving and substantially exceeds upstream references on under-served architectures; each task's interface mirrors the corresponding module in the state-of-the-art library for its architecture family, enabling direct deployment of optimized kernels into production codebases. Evaluating state-of-the-art kernel agents on FastKernels, we find that even the strongest agent achieves only 0.94×\times aggregate speedup over production baselines, with weaker agents at 0.78×0.78\times and 0.53×0.53\times -- confirming that benchmark-production misalignment is a critical bottleneck for the field. We release FastKernels as a stepping stone toward kernel agents whose benchmark gains translate directly into production throughput improvements. Code is available at https://github.com/Snowflake-AI-Research/fastkernels
Nov 2, 2026

Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization

LLM agents for GPU kernel optimization sit at two ends of a structure-freedom tradeoff. Scripted agents fix what the model does at each step, via a learned policy, an optimization menu, or fixed roles, and are sample-efficient where the recipe applies and stall where it does not. Open-ended agents let a self-directed model mutate a population of kernels and pay for the freedom in trials: thousands of evaluations, repeated edits, and wrong candidates. Both respond to hard targets by equipping the agent with more: parsed profiler output, disassembly analysis, retrieval over documentation and libraries, and stores of lessons. We argue that both lack direction, a hypothesis about where the remaining gap is, and that a short question asked at the right moment supplies it without narrowing what the agent may do next. We present KernelSeek, a question-driven agent that makes an existing CUDA kernel faster with no operator-specific knowledge and no faster implementation to imitate: a general-purpose coding agent, a minimal harness that enforces a verifiable goal, and questions at decision points, first from a human, then from a bank the agent applies to itself. On the same task, evaluator, hardware, and week, a tool-rich autonomous agent built in the prevailing style plateaued at 0.50x FlashAttention-3 after 133 model-driven steps; KernelSeek reached 1.13x. It then produced dependency-free FlashAttention forward kernels for Hopper and Blackwell, single CUDA files with no CUTLASS, CuTe, cuBLAS, or cuDNN, correct on all 182 scenarios per architecture and 1.16x FlashAttention-3 and 1.46x FlashAttention-4 (geometric mean). Across 162 human messages and 11.5K agent tool calls, every large gain followed a question that moved the agent to a different layer of the system or rejected a claimed limit, never one that supplied information. We release the kernels, harness, question bank, and all traces.
Sep 24, 2026

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted kernel optimizers can close this gap for standalone kernels, yet treat compiled models as black boxes, generally optimizing individual standalone kernels without respecting the compiler's structural decisions or verifying the model end-to-end. We present KernelOPT, a multi-agent system that treats compiled models as structured artifacts. It preserves vendor library calls (cuBLAS, cuDNN) and exclusively targets generated Triton sub-kernels using five profiling-guided LLM agents. A four-gate verification cascade applies static validation, multi-seed correctness checking, model-level float64-fallback verification, and performance gating (γ=1.03γ{=}1.03) to filter candidates and verify the re-stitched model end-to-end. When candidates fail verification, the system preserves the compiler baseline. The system accepts PyTorch nn Modules, standalone Triton kernels, and Helion kernels. Evaluated on 250 KernelBench problems (100 Level 1, 100 Level 2 and 50 Level 3) on NVIDIA H200, KernelOPT achieves geometric mean speedups over torch compile of 1.40×\times (L1), 1.15×\times (L2), and 1.07×\times (L3) across all kernels, including fallback cases. Optimized-only geomeans (excluding cases where verification gates preserve the compiler baseline) are substantially higher: 2.54×\times (L1: 36/100), 1.84×\times (L2: 23/100), and 1.37×\times (L3: 11/50), reflecting where the optimizer achieves meaningful leverage.