collaborators

7 papers

cs.DC2026

ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training

Wenxiang Lin, Xinglin Pan, Ruibo Fan +2

Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication…

cs.DC2026

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression

Ruibo Fan, Xiangrui Yu, Xinglin Pan +5

Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approach…

cs.DC2025

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism

Xinglin Pan, Shaohuai Shi, Wenxiang Lin +4

The mixture-of-experts (MoE) architecture scales model size with sublinear computational increase but suffers from memory-intensive inference due to KV caches and sparse expert act…

cs.DC2025

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap

Wenxiang Lin, Xinglin Pan, Lin Zhang +3

The sparsely activated mixture-of-experts (MoE) transformer has become a common architecture for large language models (LLMs) due to its sparsity, which requires fewer computationa…

cs.DC2025

DreamDDP: Accelerating Data Parallel Distributed LLM Training with Layer-wise Scheduled Partial Synchronization

Zhenheng Tang, Zichen Tang, Junlin Huang +7

The growth of large language models (LLMs) increases challenges of accelerating distributed training across multiple GPUs in different data centers. Moreover, concerns about data p…

cs.LG2025

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

Kunfeng Lai, Zhenheng Tang, Xinglin Pan +7

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation…