4 papers
SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates
Ziming Yu, Shuyao Xiao, Xingyu Zhao +6
Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance gradient estimators, making conv…
FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers
Peiyu Zang, Bosen Xie, Ruoxiang Xu +1
Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are limited by automatic-differenti…
KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?
Peiyu Zang, Jian Tao, Jialing Zhang +4
Modern AI systems depend on specialized accelerator kernels, whose development is complicated by increasingly diverse operators and hardware. LLMs and agentic systems promise to au…
Towards Automated Kernel Generation in the Era of LLMs
Yang Yu, Peiyu Zang, Chi Hsu Tsai +11
The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level ha…