collaborators

5 papers

cs.LG2025

EcoSpa: Efficient Transformer Training with Coupled Sparsity

Jinqi Xiao, Cheng Luo, Lingyi Huang +8

Transformers have become the backbone of modern AI, yet their high computational demands pose critical system challenges. While sparse training offers efficiency gains, existing me…

cs.LG2025

TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training

Sebastian Loeschcke, David Pitt, Robert Joseph George +5

Scientific problems require resolving multi-scale phenomena across different resolutions and learning solution operators in infinite-dimensional function spaces. Neural operators p…

cs.LG2025

MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models

Junyang Zhang, Tianyi Zhu, Cheng Luo +1

Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded…

cs.LG2025

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

Cheng Luo, Zefan Cai, Hanshi Sun +7

Transformer-based large language models (LLMs) demonstrate impressive performance in long context generation. Extending the context length has disproportionately shifted the memory…

cs.LG2024

Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training

Cheng Luo, Jiawei Zhao, Zhuoming Chen +2

We introduce Mini-Sequence Transformer (MsT), a simple and effective methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input…