activity
20242026
collaborators

5 papers

cs.DC2026

DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline

Zhenliang Xue, Hanpeng Hu, Xing Chen +7

Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible c…

cs.LG2025

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Yixin Song, Zhenliang Xue, Dongliang Wei +11

While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradig…

cs.LG2024

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Zhenliang Xue, Yixin Song, Zeyu Mi +3

Large language models (LLMs) on smartphones enable real-time AI assistance and privacy-preserving, offline operation. However, resource constraints of smartphones limit current dep…

cs.LG2024

PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU

Yixin Song, Zeyu Mi, Haotong Xie +1

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key principle…

cs.LG2024

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Yixin Song, Haotong Xie, Zhengyan Zhang +4

Exploiting activation sparsity is a promising approach to significantly accelerating the inference process of large language models (LLMs) without compromising performance. However…