4 citations · 4 across the 8 of their papers we have counts for
8 papers
A Multi-Engine Dataflow for MoE Decoding on AWS Tranium
Bin Ma, Wenjie Fan, Jialin Liu +2
Mixture-of-Experts (MoE) decoding on scratchpad-based tensor accelerators (STA) is dominated by moving expert weights while the compute engines sit idle. This traffic is hard to hi…
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
Software-based memory tiering systems decide which pages to place on the slower or faster tier. However, they do not consider two important factors that greatly influence applicati…
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…
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…
ZenFlow: Enabling Stall-Free Offloading for LLM Training
Tingfeng Lan, Yusen Wu, Bin Ma +7
Fine-tuning large language models (LLMs) often exceeds GPU memory limits, prompting systems to offload model states to CPU memory. However, existing offloaded training frameworks l…