17 citations · 17 across the 8 of their papers we have counts for
8 papers
MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches
Xin Wang, Chi Ma, Shaobin Chen +14
Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-r…
MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
Ruidong Han, Bin Yin, Shangyu Chen +12
Scaling law has been extensively validated in many domains such as natural language processing and computer vision. In the recommendation system, recent work has adopted generative…
MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan
Yuxiang Wang, Chi Ma, Xiao Yan +15
Recommendation is crucial for both user experience and company revenue in Meituan as a leading lifestyle company, and generative recommendation models (GRMs) are shown to produce q…
Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs
Yiheng Yang, Yujie Wang, Chi Ma +3
Dense large language models(LLMs) face critical efficiency bottlenecks as they rigidly activate all parameters regardless of input complexity. While existing sparsity methods(stati…
First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models
Chi Ma, Mincong Huang, Ying Zhang +5
Dynamic activation (DA) techniques, such as DejaVu and MoEfication, have demonstrated their potential to significantly enhance the inference efficiency of large language models (LL…
MOYU: A Theoretical Study on Massive Over-activation Yielded Uplifts in LLMs
Chi Ma, Mincong Huang, Chao Wang +2
Massive Over-activation Yielded Uplifts(MOYU) is an inherent property of large language models, and dynamic activation(DA) based on the MOYU property is a clever yet under-explored…
Dynamic Activation Pitfalls in LLaMA Models: An Empirical Study
Chi Ma, Mincong Huang, Chao Wang +2
In this work, we systematically investigate the efficacy of dynamic activation mechanisms within the LLaMA family of language models. Despite the potential of dynamic activation me…
Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe
Mincong Huang, Chao Wang, Chi Ma +3
Pipeline parallelism is an essential technique in the training of large-scale Transformer models. However, it suffers from imbalanced memory consumption, leading to insufficient me…