Related papers: Towards Fully-fledged GPU Multitasking via Proacti…

The exponential growth of data-intensive machine learning workloads has exposed significant limitations in conventional GPU-accelerated systems, especially when processing datasets exceeding GPU DRAM capacity. We propose MQMS, an augmented…

The ever-increasing computation and energy demand for LLM and AI agents call for holistic and efficient optimization of LLM serving systems. In practice, heterogeneous GPU clusters can be deployed in a geographically distributed manner,…

Modern GPU workloads increasingly demand efficient resource sharing, as many jobs do not require the full capacity of a GPU. Among sharing techniques, NVIDIA's Multi-Instance GPU (MIG) offers strong resource isolation by enabling…

Motivated by deep neural network applications, we study the problem of scheduling splittable jobs (e.g., neural network inference tasks) on configurable machines (e.g., multi-instance GPUs). We are given $n$ jobs and a set $C$ of…

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…

Heterogeneity has grown in popularity both at the core and server level as a way to improve both performance and energy efficiency. However, despite these benefits, scheduling applications in heterogeneous machines remains challenging.…

Scheduling real-time tasks that utilize GPUs with analyzable guarantees poses a significant challenge due to the intricate interaction between CPU and GPU resources, as well as the complex GPU hardware and software stack. While much…

Scheduling real-time tasks that utilize GPUs with analyzable guarantees poses a significant challenge due to the intricate interaction between CPU and GPU resources, as well as the complex GPU hardware and software stack. While much…

To amortize cost, cloud vendors providing DNN acceleration as a service to end-users employ consolidation and virtualization to share the underlying resources among multiple DNN service requests. This paper makes a case for a "preemptible"…

GPU singletasking is becoming increasingly inefficient and unsustainable as hardware capabilities grow and workloads diversify. We are now at an inflection point where GPUs must embrace multitasking, much like CPUs did decades ago, to meet…

High load latency that results from deep cache hierarchies and relatively slow main memory is an important limiter of single-thread performance. Data prefetch helps reduce this latency by fetching data up the hierarchy before it is…

Dataset deduplication is widely recognized as a crucial preprocessing step that enhances data quality and improves the performance of large language models. A commonly used method for this process is the MinHash Locality-Sensitive Hashing…

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…

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…

Monolithic serving with chunked prefill improves GPU utilization by batching prefill and decode together, but suffers from fine-grained phase interference. Engine-level prefill-decode (PD) disaggregation avoids interference but incurs…

Distributed cloud environments hosting data-intensive applications often experience slowdowns due to network congestion, asymmetric bandwidth, and inter-node data shuffling. These factors are typically not captured by traditional host-level…

There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of…

GPUs are broadly used in I/O-intensive big data applications. Prior works demonstrate the benefits of using GPU-side file system layer, GPUfs, to improve the GPU performance and programmability in such workloads. However, GPUfs fails to…

Efficient LLM inference scheduling is crucial for user experience. However, LLM inferences exhibit remarkable demand uncertainty (with unknown output length beforehand) and hybridity (being both compute and memory intensive). Existing LLM…

The explosive growth of AI applications has created unprecedented demand for GPU resources. Cloud providers meet this demand through GPU-as-a-Service platforms that offer rentable GPU resources for running AI workloads. In this context, the…