Related papers: CHOPtrey: contextual online polynomial extrapolati…
Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…
Massively parallel simulations of transport equation systems call for a paradigm change in algorithm development to achieve efficient scalability. Traditional approaches require time synchronization of processing elements (PEs) which…
Correlated time series analysis plays an important role in many real-world industries. Learning an efficient representation of this large-scale data for further downstream tasks is necessary but challenging. In this paper, we propose a…
To address increasing compute demand from recent multi-model workloads with heavy models like large language models, we propose to deploy heterogeneous chiplet-based multi-chip module (MCM)-based accelerators. We develop an advanced…
In this paper we analyze, evaluate, and improve the performance of training generalized linear models on modern CPUs. We start with a state-of-the-art asynchronous parallel training algorithm, identify system-level performance bottlenecks,…
Transactional Stream Processing Engines (TSPEs) form the backbone of modern stream applications handling shared mutable states. Yet, the full potential of these systems, specifically in exploiting parallelism and implementing dynamic…
The parallelized multi-retrieval architecture has been widely adopted in large-scale recommender systems for its computational efficiency and comprehensive coverage of user interests. Many retrieval methods typically integrate additional…
Improving text representation has attracted much attention to achieve expressive text-to-speech (TTS). However, existing works only implicitly learn the prosody with masked token reconstruction tasks, which leads to low training efficiency…
We present our recent code modernizations of the of the ab initio molecular dynamics program CPMD (www.cpmd.org) with a special focus on the ultra-soft pseudopotential (USPP) code path. Following the internal instrumentation of CPMD, all…
Stereo matching plays an indispensable part in autonomous driving, robotics and 3D scene reconstruction. We propose a novel deep learning architecture, which called CFP-Net, a Cross-Form Pyramid stereo matching network for regressing…
Adopting large-scale AI models in enterprise information systems is often hindered by high training costs and long development cycles, posing a significant managerial challenge. The standard end-to-end backpropagation (BP) algorithm is a…
Python is rapidly becoming the lingua franca of machine learning and scientific computing. With the broad use of frameworks such as Numpy, SciPy, and TensorFlow, scientific computing and machine learning are seeing a productivity boost on…
In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the…
The paper develops a novel design optimization framework and associated computational techniques for staged deployment optimization of complex systems under operational uncertainties. It proposes a local scenario discretization method that…
Developing an efficient code for large, multiscale astrophysical simulations is crucial in preparing the upcoming era of exascale computing. RAMSES is an astrophysical simulation code that employs parallel processing based on the Message…
Stable partitioned techniques for simulating unsteady fluid-structure interaction (FSI) are known to be computationally expensive when high added-mass is involved. Multiple coupling strategies have been developed to accelerate these…
COSA is a novel CFD system based on the compressible Navier-Stokes model for unsteady aerodynamics and aeroelasticity of fixed structures, rotary wings and turbomachinery blades. It includes a steady, time domain, and harmonic balance flow…
Transformer-based text to speech (TTS) model (e.g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e.g.,…
This study proposes a unified forecasting framework for high-dimensional multi-task time series to meet the prediction demands of cloud native backend systems operating under highly dynamic loads, coupled metrics, and parallel tasks. The…
Speculative backpropagation has emerged as a promising technique to accelerate the training of neural networks by overlapping the forward and backward passes. Leveraging speculative weight updates when error gradients fall within a specific…