7 papers
Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models
Wenjie Fan, Bin Ma, Dong Li
Attention collapse in autoregressive language models -- manifested as repetitive token loops where the model becomes trapped in self-reinforcing attractors -- is a persistent patho…
CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism
Bin Ma, Xingjian Ding, Tekin Bicer +2
Diffusion Transformers (DiTs) are increasingly adopted in scientific computing, yet growing model sizes and resolutions make distributed multi-GPU inference essential. Ulysses sequ…
TierBPF: Page Migration Admission Control for Tiered Memory via eBPF
Xi Wang, Tal Zussman, Yuang Xu +3
Existing software-based memory tiering systems decide which pages to place on the slower or faster tier. However, they do not take into account two important factors that greatly i…
cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications
Xi Wang, Bin Ma, Jongryool Kim +3
Message Passing Interface (MPI) is a foundational programming model for high-performance computing. MPI libraries traditionally employ network interconnects (e.g., Ethernet and Inf…
Machine Learning-Guided Memory Optimization for DLRM Inference on Tiered Memory
Jie Ren, Bin Ma, Shuangyan Yang +4
Deep learning recommendation models (DLRMs) are widely used in industry, and their memory capacity requirements reach the terabyte scale. Tiered memory architectures provide a cost…
mLR: Scalable Laminography Reconstruction based on Memoization
Bin Ma, Viktor Nikitin, Xi Wang +2
ADMM-FFT is an iterative method with high reconstruction accuracy for laminography but suffers from excessive computation time and large memory consumption. We introduce mLR, which…