CUDA‑Harness is a framework that enables the generation and optimization of CUDA kernels directly from natural language. It introduces Intermediate‑Structured Generation to bridge high‑level semantics with low‑level kernel code, uses Synthesis‑Based Verification to mitigate reward hacking by providing isolated test data, and employs Feedback‑Adaptive Evolution to prioritize correctness while improving performance. Experiments show the approach generalizes across different large language models, hardware platforms, and even supports C‑to‑CUDA transpilation.
By Qi Fan, An Zou, Yehan Ma
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code.
arXiv:2607. 20908v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation.
By Quazi Ishtiaque Mahmud, Nesreen K. Ahmed, Ali Jannesari
arXiv:2606. 04847v1 Announce Type: cross Abstract: Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code.
By Kun Cheng, Songshuo Lu, Sicong Liao, Tankun Li, Yafei Zhang, Dong Yang, Qiheng Lv, Hua Wang, Zhi Chen, Yaohua Tang
arXiv:2607. 24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization.
By Joshua Brodsky, Dhravid Kumar, Savini Kashmira, Jayanaka Danatanarayana, Jason Mars, Krisztian Flautner, Lingjia Tang
arXiv:2602. 11715v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation.
By Haolei Bai, Lingcheng Kong, Xueyi Chen, Jianmian Wang, Zhiqiang Tao, Huan Wang
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
arXiv:2606. 26453v1 Announce Type: new Abstract: We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) code generation with hardware profiler feedback and pluggable bottleneck detection tools.
By Jiading Gai, Shuai Zhang, Kaj Bostrom, Jin Huang, Vihang Patil, Haoyang Fang, Bernie Wang, Huzefa Rangwala, George Karypis
arXiv:2608. 12004v1 Announce Type: cross Abstract: In modern AI frameworks, GPU kernels are key to overall system performance.
By Jinjun Huang, Zhongzhen Wen, Tongtong Xu, Meng Yan, Xin Xia, Zhongxin Liu
arXiv:2607. 16241v1 Announce Type: cross Abstract: Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench.
By Yunxiang Zhang (Xiangjun), Ping Yu (Xiangjun), Jianyu Wang (Xiangjun), Max (Xiangjun), Fan, Julian Reed, Azalia Mirhoseini, Will Su
arXiv:2607. 04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA.
By Junjie Tang, Jun Huan, Hao Zhou, Yuhao Zhang, Lin Wang
arXiv:2608.21157v1 Announce Type: cross
Abstract: High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolve...
By Jinghao Wang, Qiqi Gu, Chenpeng Wu, Jianguo Yao, Haibing Guan, Xijun Li