Related papers: Balancing Computation Load and Representation Expr…
We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…
Fluid motion can be considered as a point cloud transformation when using the SPH method. Compared to traditional numerical analysis methods, using machine learning techniques to learn physics simulations can achieve near-accurate results,…
Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on these models, by design, harnesses a temporal dependency, where…
Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…
Flow fields are often partitioned into data blocks for massively parallel computation and analysis based on blockwise relationships. However, most of the previous techniques only consider the first-order dependencies among blocks, which is…
Efficient and sustainable power generation is a crucial concern in the energy sector. In particular, thermal power plants grapple with accurately predicting steam mass flow, which is crucial for operational efficiency and cost reduction. In…
This paper first presents a parallel solution for the Flowshop Scheduling Problem in parallel environment, and then proposes a novel load balancing strategy. The proposed Proportional Fairness Strategy (PFS) takes computational performance…
Efficient parallel computing has become a pivotal element in advancing artificial intelligence. Yet, the deployment of Spiking Neural Networks (SNNs) in this domain is hampered by their inherent sequential computational dependency. This…
Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique…
Spiking Neural Network (SNN), as a brain-inspired and energy-efficient network, is currently facing the pivotal challenge of exploring a suitable and efficient learning framework. The predominant training methodologies, namely…
We introduce FFN Fusion, an architectural optimization technique that reduces sequential computation in large language models by identifying and exploiting natural opportunities for parallelization. Our key insight is that sequences of…
Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables…
Hybrid parallelism underpins large-scale LLM training across tens of thousands of GPUs. At such scale, hardware failures on individual devices lead to performance skew across devices, diminishing overall training efficiency. Existing…
Hybrid parallelism techniques are essential for efficiently training large language models (LLMs). Nevertheless, current automatic parallel planning frameworks often overlook the simultaneous consideration of node heterogeneity and dynamic…
Hybrid models that combine state space models (SSMs) with attention mechanisms have shown strong performance by leveraging the efficiency of SSMs and the high recall ability of attention. However, the architectural design choices behind…
Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…
Generative Artificial Intelligence (AI) has become incredibly popular in recent years, and the significance of traditional accelerators in dealing with large-scale parameters is urgent. With the diffusion model's parallel structure, the…
Spiking Neural Networks (SNN) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge devices through asynchronous and sparse processing. However, being temporal models, SNNs depend…
The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…
Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…