English
Related papers

Related papers: Async-fork: Mitigating Query Latency Spikes Incurr…

200 papers

Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at kernel boundaries, utilizing only 21% of their peak memory…

Web caching is essential for the World Wide Web, saving processing power, bandwidth, and reducing latency. Many proxy caching solutions focus on buffering data from the main server, neglecting cacheable information meant for server writes.…

Databases · Computer Science 2024-10-15 Ionut-Alex Moise , Alexandra Băicoianu

Kernel functions are vital ingredients of several machine learning algorithms, but often incur significant memory and computational costs. We introduce an approach to kernel approximation in machine learning algorithms suitable for…

Sparsity is an intrinsic property of convolutional neural network(CNN) and worth exploiting for CNN accelerators, but extra processing comes with hardware overhead, causing many architectures suffering from only minor profit. Meanwhile,…

Hardware Architecture · Computer Science 2022-09-26 Wenhao Sun , Deng Liu , Zhiwei Zou , Wendi Sun , Yi Kang , Song Chen

Self-attention is an essential component of large language models (LLM) but a significant source of inference latency for long sequences. In multi-tenant LLM serving scenarios, the compute and memory operation cost of self-attention can be…

Machine Learning · Computer Science 2024-08-02 Lu Ye , Ze Tao , Yong Huang , Yang Li

Emerging non-volatile memory (NVM) technologies promise memory speed byte-addressable persistent storage with a load/store interface. However, programming applications to directly manipulate NVM data is complex and error-prone. Applications…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-01 Pradeep Fernando , Irina Calciu , Jayneel Gandhi , Aasheesh Kolli , Ada Gavrilovska

The emergence of Big Data in recent years has resulted in a growing need for efficient data processing solutions. While infrastructures with sufficient compute power are available, the I/O bottleneck remains. The Linux page cache is an…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-06 Hoang-Dung Do , Valerie Hayot-Sasson , Rafael Ferreira da Silva , Christopher Steele , Henri Casanova , Tristan Glatard

Rise of hundreds cores technologies bring again to the first plan the problem of interprocess synchronization in database engines. Spinlocks are widely used in contemporary DBMS to synchronize processes at microsecond timescale. Latches are…

Databases · Computer Science 2011-11-03 Andrey Nikolaev

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM)…

Hardware Architecture · Computer Science 2021-09-15 Mohammed Elbtity , Abhishek Singh , Brendan Reidy , Xiaochen Guo , Ramtin Zand

Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. However, the growth of the KV cache in response to increasing…

Computation and Language · Computer Science 2024-06-18 Yuhong Li , Yingbing Huang , Bowen Yang , Bharat Venkitesh , Acyr Locatelli , Hanchen Ye , Tianle Cai , Patrick Lewis , Deming Chen

At the edge, there is a high level of similarity in computing. One approach that has been proposed to enhance the efficiency of edge computing is computation reuse, which eliminates redundant computations. Edge computing is integrated with…

Networking and Internet Architecture · Computer Science 2025-02-05 Atiyeh Javaheri , Ali Bohlooli , Kamal Jamshidi

Two characteristics that make convex decomposition algorithms attractive are simplicity of operations and generation of parallelizable structures. In principle, these schemes require that all coordinates update at the same time, i.e., they…

Optimization and Control · Mathematics 2018-03-07 Giorgos Stathopoulos , Colin N. Jones

Protected user-level libraries have been proposed as a way to allow mutually distrusting applications to safely share kernel-bypass services. In this paper, we identify and solve several previously unaddressed obstacles to realizing this…

Operating Systems · Computer Science 2025-09-04 Alan Beadle , Michael L. Scott , John Criswell

Operating Systems enforce logical isolation using abstractions such as processes, containers, and isolation technologies to protect a system from malicious or buggy code. In this paper, we show new types of side channels through the file…

Cryptography and Security · Computer Science 2025-04-29 Cheng Gu , Yicheng Zhang , Nael Abu-Ghazaleh

Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…

Artificial Intelligence · Computer Science 2025-04-17 Hyungwoo Lee , Kihyun Kim , Jinwoo Kim , Jungmin So , Myung-Hoon Cha , Hong-Yeon Kim , James J. Kim , Youngjae Kim

Brain-inspired Spiking Neural Networks (SNNs) have attracted attention for their event-driven characteristics and high energy efficiency. However, the temporal dependency and irregularity of spikes present significant challenges for…

Hardware Architecture · Computer Science 2025-06-11 Kainan Wang , Chengyi Yang , Chengting Yu , Yee Sin Ang , Bo Wang , Aili Wang

Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-world studies reveal that over 70% of user requests to LLMs…

Machine Learning · Computer Science 2025-09-05 Yifan Yu , Yu Gan , Nikhil Sarda , Lillian Tsai , Jiaming Shen , Yanqi Zhou , Arvind Krishnamurthy , Fan Lai , Henry M. Levy , David Culler

Inference is now the dominant AI workload, yet existing systems force trade-offs between latency, throughput, and cost. Arctic Inference, an open-source vLLM plugin from Snowflake AI Research, introduces Shift Parallelism, a dynamic…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-17 Samyam Rajbhandari , Mert Hidayetoglu , Aurick Qiao , Ye Wang , Juncheng Yang , Jeff Rasley , Michael Wyatt , Yuxiong He

Today's datacenter applications are underpinned by datastores that are responsible for providing availability, consistency, and performance. For high availability in the presence of failures, these datastores replicate data across several…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-01-28 A. Katsarakis , V. Gavrielatos , M. Katebzadeh , A. Joshi , A. Dragojevic , B. Grot , V. Nagarajan

Language models (LMs) underpin emerging mobile and embedded AI applications like meeting and video summarization and document analysis, which often require processing multiple long-context inputs. Running an LM locally on-device improves…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-15 Huawei Zhang , Chunwei Xia , Zheng Wang