Related papers: Cornserve: A Distributed Serving System for Any-to…

Today's highly heterogeneous computing landscape places a burden on programmers wanting to achieve high performance on a reasonably broad cross-section of machines. To do so, computations need to be expressed in many different but…

Biological neural networks are often modeled as systems of coupled, nonlinear, ordinary or partial differential equations. The number of differential equations used to model a network increases with the size of the network and the level of…

While ML model training and inference are both GPU-intensive, CPU-based data processing is often the bottleneck. Distributed data processing systems based on the batch or stream processing models assume homogeneous resource requirements.…

We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to…

TensorX is a Python library for prototyping, design, and deployment of complex neural network models in TensorFlow. A special emphasis is put on ease of use, performance, and API consistency. It aims to make available high-level components…

Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness…

Distributed-Something coordinates the distribution of any Dockerized workflow using on-demand computational infrastructure from Amazon Web Services to enable at-scale workflows where neither computing power nor data storage are limited by…

Machine learning (ML) models are increasingly deployed to production, calling for efficient inference serving systems. Efficient inference serving is complicated by two challenges: (i) ML models incur high computational costs, and (ii) the…

Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have…

A hallmark of human intelligence is the ability to create complex artifacts through structured multi-step processes. Generating procedural tutorials with AI is a longstanding but challenging goal, facing three key obstacles: (1) scarcity of…

Multimodal large language models (MLLMs) extend the capabilities of large language models (LLMs) by combining heterogeneous model architectures to handle diverse modalities like images and audio. However, this inherent heterogeneity in MLLM…

Large multimodal models (LMMs) typically employ an encoding module to transform multimodal data inputs into embeddings, which are then fed to language models for further processing. However, efficiently serving LMMs remains highly…

A client-server architecture to simultaneously solve multiple learning tasks from distributed datasets is described. In such architecture, each client is associated with an individual learning task and the associated dataset of examples.…

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver…

Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…

Recently, large-scale generative models have demonstrated outstanding text-to-image generation capabilities. However, generating high-fidelity personalized images with specific subjects still presents challenges, especially in cases…

With the evolution of microservice applications, the underlying architectures have become increasingly complex compared to their monolith counterparts. This mainly brings in the challenge of observability. By providing a deeper…

Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversity (various prefixes and tidal requests), treating all the…

By imitating the synaptic connectivity and plasticity of the brain, emerging electronic nanodevices offer new opportunities as the building blocks of neuromorphic systems. One challenge for largescale simulations of computational…

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather…