arXiv AI September 11, 2026 By Peiyu Zang, Jian Tao, Jialing Zhang, Yichen Yuan, Wentao Zhang, Guang Liu, Yonghua Lin

KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?

KernelGenBench is a unified benchmark that evaluates large language models and agentic systems for generating efficient Triton kernels across diverse operator sources and hardware platforms. It covers 210 operators from PyTorch ATen, vLLM, and cuBLAS, and tests a 110‑operator subset on six different chips, consuming over 15 billion tokens in evaluation. The study finds that no single method dominates across all sources and platforms, with significant variations in correctness and performance depending on the operator source and hardware, and that agentic approaches require millions of tokens per successful operator.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 31

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation

arXiv:2607. 27231v1 Announce Type: cross Abstract: Large language models (LLMs) have significantly increased the demand for efficient accelerator kernels, but kernel development remains a highly specialized and labor-intensive task.

By Peiyu Zang, Jian Tao, Jialing Zhang, Yichen Yuan, Wentao Zhang, Guang Liu, Yonghua Lin

llms agents benchmarks

arXiv Machine Learning

Jun 3

KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators

arXiv:2606. 02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators.

By Taras Sereda, Burak Bartan, Ankita Nayak, Tom St. John, Natalie Serrino, Zain Asgar

llms agents efficiency benchmarks

arXiv AI

Jul 17

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

arXiv:2607. 14541v1 Announce Type: new Abstract: Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads.

By Lingyun Yang, Yuxiao Wang, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang, Yinghao Yu, Guodong Yang, Liping Zhang

llms rag agents benchmarks

arXiv AI

Sep 25

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

KernelOPT is a multi‑agent system that optimizes GPU kernels generated by compilers like PyTorch Inductor by treating compiled models as structured artifacts. It preserves vendor library calls and focuses on Triton sub‑kernels, using five profiling‑guided LLM agents and a four‑gate verification cascade to ensure correctness and performance before re‑stitching the model. On 250 KernelBench problems, KernelOPT achieves geometric mean speedups of 1.40×, 1.15×, and 1.07× over torch.compile at three optimization levels.

By Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur

llms agents

Hugging Face Trending Papers

Sep 24

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

KernelOPT is a multi-agent system that optimizes GPU kernels generated by compilers like PyTorch Inductor by treating compiled models as structured artifacts. It preserves vendor library calls and focuses on Triton sub-kernels, using five profiling-guided LLM agents and a four-gate verification cascade to filter and validate candidates. On 250 KernelBench problems, KernelOPT achieves geometric mean speedups of 1.40×, 1.15×, and 1.07× over torch.compile at different optimization levels.

llms agents

arXiv Machine Learning

Jun 5

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

arXiv:2604. 01489v2 Announce Type: replace Abstract: High-performance GPU kernels are critical to modern machine learning systems, yet developing them remains a manual, expert-driven process.

By Tara Saba, Zhiyang Chen, Jikai Jason Li, Anne Ouyang, Xujie Si, Fan Long

llms agents benchmarks

One email a morning, machine-written

Related stories

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation

KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe