English
Related papers

Related papers: Training Foundation Models on a Full-Stack AMD Pla…

200 papers

Large and sparse feed-forward layers (S-FFN) such as Mixture-of-Experts (MoE) have proven effective in scaling up Transformers model size for \textit{pretraining} large language models. By only activating part of the FFN parameters…

Computation and Language · Computer Science 2023-10-25 Zeyu Leo Liu , Tim Dettmers , Xi Victoria Lin , Veselin Stoyanov , Xian Li

The Mixture of Experts (MoE) architecture is a cornerstone of modern state-of-the-art (SOTA) large language models (LLMs). MoE models facilitate scalability by enabling sparse parameter activation. However, traditional MoE architecture uses…

Computation and Language · Computer Science 2025-08-12 Haoyuan Wu , Haoxing Chen , Xiaodong Chen , Zhanchao Zhou , Tieyuan Chen , Yihong Zhuang , Guoshan Lu , Zenan Huang , Junbo Zhao , Lin Liu , Zhenzhong Lan , Bei Yu , Jianguo Li

Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the scaling capability of masked image modeling (MIM) methods…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Cheng-Ze Lu , Xiaojie Jin , Qibin Hou , Jun Hao Liew , Ming-Ming Cheng , Jiashi Feng

In today's landscape, Mixture of Experts (MoE) is a crucial architecture that has been used by many of the most advanced models. One of the major challenges of MoE models is that they usually require much more memory than their dense…

Machine Learning · Computer Science 2025-11-11 Shuning Lin , Yifan He , Yitong Chen

Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains…

Computation and Language · Computer Science 2026-02-11 Nam V. Nguyen , Thong T. Doan , Luong Tran , Van Nguyen , Quang Pham

The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is constrained by limited…

Artificial Intelligence · Computer Science 2026-05-05 Guoying Zhu , Meng Li , Haipeng Dai , Xuechen Liu , Weijun Wang , Keran Li , Jun xiao , Ligeng Chen , Wei Wang

Large scale deep Convolution Neural Networks (CNNs) increasingly demands the computing power. It is key for researchers to own a great powerful computing platform to leverage deep learning (DL) advancing.On the other hand, as the…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Xin Chen , Hua Zhou , Yuxiang Gao , Yu Zhu

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Artificial Intelligence · Computer Science 2025-10-01 Yixiao Chen , Yanyue Xie , Ruining Yang , Wei Jiang , Wei Wang , Yong He , Yue Chen , Pu Zhao , Yanzhi Wang

Hybrid Mamba-Transformer networks have recently garnered broad attention. These networks can leverage the scalability of Transformers while capitalizing on Mamba's strengths in long-context modeling and computational efficiency. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Yunze Liu , Li Yi

Engineering complex systems (aircraft, buildings, vehicles) requires coordinating geometric and performance couplings across subsystems. As generative models proliferate for specialized domains, a key research gap is how to coordinate…

Computational Engineering, Finance, and Science · Computer Science 2026-04-08 Tim Aebersold , Soheyl Massoudi , Mark D. Fuge

We present IMU-1, a 430M-parameter language model trained on 72B tokens that approaches the benchmark performance of models trained on 56x more data. We describe a validated training recipe combining recent architectural interventions…

Machine Learning · Computer Science 2026-02-04 George Grigorev

The emergence of Superchips represents a significant advancement in next-generation AI hardware. These Superchips employ a tightly coupled heterogeneous architecture that integrates GPU and CPU on the same package, which offers…

Machine Learning · Computer Science 2025-09-26 Xinyu Lian , Masahiro Tanaka , Olatunji Ruwase , Minjia Zhang

There has been an explosion of interest in designing high-performance Transformers. While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Zizheng Pan , Peng Chen , Haoyu He , Jing Liu , Jianfei Cai , Bohan Zhuang

The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges at scale due to the…

Computation and Language · Computer Science 2023-09-12 Ted Zadouri , Ahmet Üstün , Arash Ahmadian , Beyza Ermiş , Acyr Locatelli , Sara Hooker

The Mixture-of-Experts (MoE) architecture is crucial for scaling large language models, but its scalability is severely limited by inter-GPU communication bottlenecks in multi-GPU systems. Although overlapping communication with computation…

Hardware Architecture · Computer Science 2026-05-08 Zhuoshan Zhou , Chen Zhang , Shuyi Zhang , Qijun Zhang , Haibo Wang , Zhe Zhou , Zhipeng Tu , Guangyu Sun , Yijia Diao , Zhigang Ji , Jingwen Leng , Guanghui He , Minyi Guo

Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adopt the following setting: 1) use FLOPs or activated…

Machine Learning · Computer Science 2024-07-02 Xianzhi Du , Tom Gunter , Xiang Kong , Mark Lee , Zirui Wang , Aonan Zhang , Nan Du , Ruoming Pang

Sparsely-activated Mixture-of-Experts (MoE) architecture has increasingly been adopted to further scale large language models (LLMs). However, frequent failures still pose significant challenges as training scales. The cost of even a single…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-27 Yongji Wu , Wenjie Qu , Xueshen Liu , Tianyang Tao , Yifan Qiao , Zhuang Wang , Wei Bai , Yuan Tian , Jiaheng Zhang , Z. Morley Mao , Matthew Lentz , Danyang Zhuo , Ion Stoica

Mixture-of-Expert (MoE) presents a strong potential in enlarging the size of language model to trillions of parameters. However, training trillion-scale MoE requires algorithm and system co-design for a well-tuned high performance…

Machine Learning · Computer Science 2021-03-25 Jiaao He , Jiezhong Qiu , Aohan Zeng , Zhilin Yang , Jidong Zhai , Jie Tang

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Biyao Zhang , Mingkai Zheng , Debargha Ganguly , Xuecen Zhang , Vikash Singh , Vipin Chaudhary , Zhao Zhang

Neural operators have emerged as an efficient paradigm for solving PDEs, overcoming the limitations of traditional numerical methods and significantly improving computational efficiency. However, due to the diversity and complexity of PDE…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Dengdi Sun , Xiaoya Zhou , Xiao Wang , Hao Si , Wanli Lyu , Jin Tang , Bin Luo