11 papers
Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory
Siyuan Chen, Runlin Hou, Shenxiu Wu +7
Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process, and stronger foundation mod…
AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
Junhao Qiu, Zidong Wang, Yansong Sun +3
Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but requires deep hardware expertise. While large language models (LLMs) have show…
Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed
Haokun Lin, Kaijie Zhu, Haobo Xu +4
Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenario…
Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels
Yansong Sun, Shenxiu Wu, Siyuan Chen +6
Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness throu…
DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization
Haokun Lin, Xinle Jia, Haobo Xu +7
The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrate for efficient LLM inference,…
ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation
Zhe Zhao, Haibin Wen, Jiaming Ma +4
An important recurring pattern in scientific breakthroughs is a two-stage process: an initial phase of undirected experimentation that yields an unexpected finding, followed by a r…
CDEoH: Category-Driven Automatic Algorithm Design With Large Language Models
Yu-Nian Wang, Shen-Huan Lyu, Ning Chen +3
With the rapid advancement of large language models (LLMs), LLM-based heuristic search methods have demonstrated strong capabilities in automated algorithm generation. However, the…
Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization
Junhao Qiu, Xin Chen, Liang Ge +3
Neighborhood search operators are critical to the performance of Multi-Objective Evolutionary Algorithms (MOEAs) and rely heavily on expert design. Although recent LLM-based Automa…
EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
Ping Guo, Chenyu Zhu, Siyuan Chen +4
CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. D…
Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models
Siyuan Chen, Zhichao Lu, Qingfu Zhang
Automated kernel design is critical for overcoming software ecosystem barriers in emerging hardware platforms like RISC-V. While large language models (LLMs) have shown promise for…
Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Haokun Lin, Haobo Xu, Yichen Wu +6
Recent advances in diffusion large language models (dLLMs) have introduced a promising alternative to autoregressive (AR) LLMs for natural language generation tasks, leveraging ful…