Related papers: Mercury: QoS-Aware Tiered Memory System
Providing minimum quality-of-service (QoS) in crowded wireless communications systems, with high user density, is challenging due to the network structure with limited transmit power budget and resource blocks. Smart resource allocation…
Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale…
Cloud-based serverless computing systems, either public or privately provisioned, aim to provide the illusion of infinite resources and abstract users from details of the allocation decisions. With the goal of providing a low cost and a…
The rise of microservice architectures has revolutionized application design, fostering adaptability and resilience. These architectures facilitate scaling and encourage collaborative efforts among specialized teams, streamlining deployment…
Successful sequential recommendation systems rely on accurately capturing the user's short-term and long-term interest. Although Transformer-based models achieved state-of-the-art performance in the sequential recommendation task, they…
Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…
Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are…
High capacity and scalable memory systems play a vital role in enabling our desktops, smartphones, and pervasive technologies like Internet of Things (IoT). Unfortunately, memory systems are becoming increasingly prone to faults. This is…
This paper addresses joint admission control and per-user equipment (UE) bandwidth allocation to maximize weighted sum-rate in network slicing-enabled user-centric cell-free (CF) massive multiple-input multiple-output (mMIMO) systems when…
These days enterprise applications try to integrate online processing and batch jobs into a common software stack for seamless monitoring and driverless operations. Continuous integration of these systems results in choking of the poorly…
Cloud computing facilitates the access of applications and data from any location by a distributed storage system. Erasure codes offer better data replication technique with reduced storage costs for more reliability. This paper considers…
Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…
To realize the long-standing vision of providing quality-of-service (QoS) guarantees on a public Internet, this paper introduces Hummingbird: a lightweight QoS-system that provides fine-grained inter-domain reservations for end hosts.…
In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable…
Serving LLMs with a cluster of GPUs is common nowadays, where the serving system must meet strict latency SLOs required by applications. However, the stateful nature of LLM serving requires maintaining huge states (i.e., KVCache) in limited…
Amidst the recent strides in evaluating Large Language Models for Code (Code LLMs), existing benchmarks have mainly focused on the functional correctness of generated code, neglecting the importance of their computational efficiency. To…
As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely…
Traditionally, query optimizers have been designed for computer systems that share a common architecture, consisting of a CPU, main memory and disk subsystem. The efficiency of query optimizers and their successful employment relied on the…
Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across…
The Compute Express Link (CXL) technology facilitates the extension of CPU memory through byte-addressable SerDes links and cascaded switches, creating complex heterogeneous memory systems where CPU access to various endpoints differs in…