Related papers: Towards Fast Setup and High Throughput of GPU Serv…
General sparse matrix-matrix multiplication (SpGEMM) is a fundamental building block for numerous applications such as algebraic multigrid method (AMG), breadth first search and shortest path problem. Compared to other sparse BLAS routines,…
Serverless computing increases developer productivity by removing operational concerns such as managing hardware or software runtimes. Developers, however, still need to partition their application into functions, which can be error-prone…
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…
Successfully solving long-horizon manipulation tasks remains a fundamental challenge. These tasks involve extended action sequences and complex object interactions, presenting a critical gap between high-level symbolic planning and…
In order to satisfy timing constraints, modern real-time applications require massively parallel accelerators such as General Purpose Graphic Processing Units (GPGPUs). Generation after generation, the number of computing clusters made…
Graph processing systems are essential for analyzing large-scale data with complex relationships, yet most existing frameworks rely on statically provisioned clusters, resulting in poor elasticity and inefficient resource utilization under…
Serverless computing is becoming widely adopted among cloud providers, thus making increasingly popular the Function-as-a-Service (FaaS) programming model, where the developers realize services by packaging sequences of stateless function…
Serverless computing is a popular cloud computing paradigm that has found widespread adoption across various online workloads. It allows software engineers to develop cloud applications as a set of functions (called serverless functions).…
Non-volatile main memory (NVRAM) technologies provide an attractive set of features for large-scale graph analytics, including byte-addressability, low idle power, and improved memory-density. NVRAM systems today have an order of magnitude…
Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…
Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization…
The sizes of GPU applications are rapidly growing. They are exhausting the compute and memory resources of a single GPU, and are demanding the move to multiple GPUs. However, the performance of these applications scales sub-linearly with…
Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed workload execution. Such modeling is essential for pre-deployment…
Industrial and government organizations increasingly depend on data-driven analytics for workforce, finance, and regulated decision processes, where timeliness, cost efficiency, and compliance are critical. Distributed frameworks such as…
Simulations of physical phenomena are essential to the expedient design of precision components in aerospace and other high-tech industries. These phenomena are often described by mathematical models involving partial differential equations…
Serverless computing is a promising approach for edge computing since its inherent features, e.g., lightweight virtualization, rapid scalability, and economic efficiency. However, previous studies have not studied well the issues of…
Training modern neural networks on large datasets is computationally and energy intensive. We present SAGE, a streaming data-subset selection method that maintains a compact Frequent Directions (FD) sketch of gradient geometry in $O(\ell…
Effective mental health counseling is a complex, theory-driven process requiring the simultaneous integration of psychological frameworks, real-time distress signals, and strategic intervention planning. This level of clinical reasoning is…
GPU-accelerated computing is a key technology to realize high-speed inference servers using deep neural networks (DNNs). An important characteristic of GPU-based inference is that the computational efficiency, in terms of the processing…
With the advent of AWS Lambda in 2014, Serverless Computing, particularly Function-as-a-Service (FaaS), has witnessed growing popularity across various application domains. FaaS enables an application to be decomposed into fine-grained…