Related papers: Optimal Workload Placement on Multi-Instance GPUs

Mapping parallel threads onto non-box-shaped domains is a known challenge in GPU computing; efficient mapping prevents performance penalties from unnecessary resource allocation. Currently, achieving this requires significant analytical…

The high memory and computation demand of large language models (LLMs) makes them challenging to be deployed on consumer devices due to limited GPU memory. Offloading can mitigate the memory constraint but often suffers from low GPU…

GPU underutilization is a significant concern in many production deep learning clusters, leading to prolonged job queues and increased operational expenses. A promising solution to this inefficiency is GPU sharing, which improves resource…

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…

GPU (graphics processing unit) has been used for many data-intensive applications. Among them, deep learning systems are one of the most important consumer systems for GPU nowadays. As deep learning applications impose deeper and larger…

The exponential growth of computational workloads is surpassing the capabilities of conventional architectures, which are constrained by fundamental limits. In-memory computing (IMC) with RRAM provides a promising alternative by providing…

Transformers and large language models~(LLMs) have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is very…

3D Gaussian splatting (3DGS) is a transformative technique with profound implications on novel view synthesis and real-time rendering. Given its importance, there have been many attempts to improve its performance. However, with the…

Hybrid CPU-GPU algorithms for Algebraic Multigrid methods (AMG) to efficiently utilize both CPU and GPU resources are presented. In particular, hybrid AMG framework focusing on minimal utilization of GPU memory with performance on par with…

Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating LLM pre-training, fine-tuning, and inference. Training and…

Multi-tenant machine learning services have become emerging data-intensive workloads in data centers with heavy usage of GPU resources. Due to the large scale, many tuning parameters and heavy resource usage, it is usually impractical to…

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…

Serving large language models (LLMs) for massive users is challenged by the significant memory footprint of the transient state, known as the key-value (KV) cache, which scales with sequence length and number of requests. Instead of renting…

Personalized recommendation is a ubiquitous application on the internet, with many industries and hyperscalers extensively leveraging Deep Learning Recommendation Models (DLRMs) for their personalization needs (like ad serving or movie…

LLM-based applications have been widely used in various industries, but with the increasing of models size, an efficient large language model (LLM) inference system is an urgent problem to be solved for service providers. Since the…

Multigrid algorithms are among the fastest iterative methods known today for solving large linear and some non-linear systems of equations. Greatly optimized for serial operation, they still have a great potential for parallelism not fully…

Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption.…

The High Performance Computing (HPC) field is witnessing a widespread adoption of Graphics Processing Units (GPUs) as co-processors for conventional homogeneous clusters. The adoption of prevalent Single- Program Multiple-Data (SPMD)…

Modern Machine Learning (ML) training on large-scale datasets is a very time-consuming workload. It relies on the optimization algorithm Stochastic Gradient Descent (SGD) due to its effectiveness, simplicity, and generalization performance.…