Related papers: Accelerating Recommender Model ETL with a Streamin…
Mixture-of-Experts (MoE) model architecture has emerged as a promising solution for scaling transformer models efficiently, offering sparse activation that reduces computational costs while increasing model capacity. However, as MoE models…
Transformer-based neural models are used in many AI applications. Training these models is expensive, as it takes huge GPU resources and long duration. It is challenging because typical data like sentences have variable lengths, and…
Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models rely on terabyte-scale embedding tables to learn user…
Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that…
When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny…
Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdependencies of nodes, existing TIG embedding models need to…
Evolutionary Reinforcement Learning (EvoRL) has emerged as a promising approach to overcoming the limitations of traditional reinforcement learning (RL) by integrating the Evolutionary Computation (EC) paradigm with RL. However, the…
Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference…
Leveraging Graphics Processing Units (GPUs) to accelerate scientific software has proven to be highly successful, but in order to extract more performance, GPU programmers must overcome the high latency costs associated with their use. One…
The parameter size of modern large language models (LLMs) can be scaled up via the sparsely-activated Mixture-of-Experts (MoE) technique to avoid excessive increase of the computational costs. To further improve training efficiency,…
The Mixture-of-Experts (MoE) architecture has become increasingly popular as a method to scale up large language models (LLMs). To save costs, heterogeneity-aware training solutions have been proposed to utilize GPU clusters made up of both…
Graphics processors, or GPUs, have recently been widely used as accelerators in the shared environments such as clusters and clouds. In such shared environments, many kernels are submitted to GPUs from different users, and throughput is an…
Developing efficient GPU kernels can be difficult because of the complexity of GPU architectures and programming models. Existing performance tools only provide coarse-grained suggestions at the kernel level, if any. In this paper, we…
We introduce CuLE (CUDA Learning Environment), a CUDA port of the Atari Learning Environment (ALE) which is used for the development of deep reinforcement algorithms. CuLE overcomes many limitations of existing CPU-based emulators and…
In this paper, we systematically evaluate the inference performance of the Edge TPU by Google for neural networks with different characteristics. Specifically, we determine that, given the limited amount of on-chip memory on the Edge TPU,…
Realistic recommender systems are often required to adapt to ever-changing data and tasks or to explore different models systematically. To address the need, we present AutoRec, an open-source automated machine learning (AutoML) platform…
Recently, Mixture-of-Experts (MoE) has become one of the most popular techniques to scale pre-trained models to extraordinarily large sizes. Dynamic activation of experts allows for conditional computation, increasing the number of…
Sequential recommender systems (SRS) have become the key technology in capturing user's dynamic interests and generating high-quality recommendations. Current state-of-the-art sequential recommender models are typically based on a…
This paper presents PipeBoost, a low-latency LLM serving system for multi-GPU (serverless) clusters, which can rapidly launch inference services in response to bursty requests without preemptively over-provisioning GPUs. Many LLM inference…
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…