Xinguo Zhu — accepted AI-conference papers

2026

QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation

Xinguo Zhu, Shaohui Peng, Jiaming Guo, Yunji Chen, Qi Guo, Yuanbo Wen +7

AAAI 2026technical

Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While large language models (LLMs) offer promise for automation, both general-purpose and finetuned LLMs suffer from two fundament

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

QiMeng-TensorOp: One-Line Prompt is Enough for High-Performance Tensor Operator Generation with Hardware Primitives

Xuzhi Zhang, Shaohui Peng, Qirui Zhou, Yuanbo Wen, Qi Guo, Ruizhi Chen +9

IJCAI 2025

Computation-intensive tensor operators constitute over 90% of the computations in Large Language Models (LLMs) and Deep Neural Networks. Automatically and efficiently generating high-performance tensor operators with hardware primitives is crucial for diverse and ever-evolving hardware architectures

Cited by 0 Source ↗PDF ↗Scholar ↗