Published in PEARC 2024, 2024
MLPerf BERT Inference Benchmark results on AMD Instinct GPUs
Recommended citation: Z. Wang, K. Vu, M. Hodak, A. Mehrotra, F. Gutierrez, K. Smith, G. Seo, et al. "Preliminary Results of the MLPerf BERT Inference Benchmark on AMD Instinct GPUs." Practice and Experience in Advanced Research Computing 2024: Human Powered Computing.
Published in arXiv preprint, 2025
Using large language models to predict GPU kernel performance
Recommended citation: Z. Wang, C. Ramos, M. A. Awad, K. Lowery. "Omniwise: Predicting GPU Kernels Performance with LLMs." arXiv preprint arXiv:2506.20886.
Download Paper
Published in AAAI 2026 (Oral), 2026
AAAI 2026 (Oral).
Recommended citation: P. Naidu, Z. Wang, L. Bergen, R. Paturi. "Quiet Feature Learning in Algorithmic Tasks." AAAI Conference on Artificial Intelligence (AAAI), 2026. Oral.
Download Paper
Published in COLM 2026, 2026
Accepted to COLM 2026. Encoding documents independently and pooling their states in Mamba2 models.
Recommended citation: Y. Jafari*, Z. Wang*, L. Bergen, T. Berg-Kirkpatrick. "The Surprising Soupability of Documents in State Space Models." Conference on Language Modeling (COLM), 2026.
Download Paper
Published in SC 2026, 2026
Accepted to SC26. Scaling trillion-parameter Mixture-of-Experts training on hierarchical HPC systems.
Recommended citation: Z. Wang, L. Jing, E. Herron, S. Dash, F. Wang, M. Zhang. "X-MoE-4D: Breaking the Scaling Barrier for Trillion Parameter MoEs on Hierarchical HPC Systems." The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC26), 2026.