KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation
High-performance GPU kernels are essential to modern machine learning systems, yet automatically generating kernels that are both correct and efficient remains challenging. Existing LLM-based approaches face two major limitations: the scarcity of high-quality training data aligned with the model's current capabilities, and the inherent trade-off between kernel correctness and performance. To address these challenges, we propose KernelZero, a co-evolution framework that continuously improves GPU kernel generation through two specialized models: a Proposer that generates Torch modules from API sets and a Coder that translates them into CUDA or Triton kernels. KernelZero uses a frontier-driv...
| Authors | Changxin Ke, Rui Zhang, Zixiang Fang et al. |
|---|---|
| Primary category | cs.LG |
| Published | 27 September 2026 |
| Last updated at source | 27 September 2026 |
Connected in the knowledge graph
- kcxain/KernelZero-CUDA-SFT-7BModel · cited by
- kcxain/KernelZero-CUDA-7BModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.