Related papers: Enlightening Flash Storage to Stream Writes by Obj…

Large language models (LLMs) are increasingly being deployed on mobile devices, but the limited DRAM capacity constrains the deployable model size. This paper introduces ActiveFlow, the first LLM inference framework that can achieve…

Application designers often face the question of whether to store large objects in a filesystem or in a database. Often this decision is made for application design simplicity. Sometimes, performance measurements are also used. This paper…

Bridging different modalities lies at the heart of cross-modality generation. While conventional approaches treat the text modality as a conditioning signal that gradually guides the denoising process from Gaussian noise to the target image…

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…

Linearizable datastores are desirable because they provide users with the illusion that the datastore is run on a single machine that performs client operations one at a time. To reduce the performance cost of providing this illusion, many…

Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previously computed states for the beginning part of a request (prefix), when another request starts with…

Diffraction drastically limits the bit density in optical data storage. To increase the storage density, alternative strategies involving supplementary recording dimensions and robust read-out schemes must be explored. Here, we propose to…

Although read disturbance has emerged as a major reliability concern, managing read disturbance in modern NAND flash memory has not been thoroughly investigated yet. From a device characterization study using real modern NAND flash memory,…

NAND flash memory is ubiquitous in everyday life today because its capacity has continuously increased and cost has continuously decreased over decades. This positive growth is a result of two key trends: (1) effective process technology…

The ever-increasing sizes of large language models necessitate distributed solutions for fast inference that exploit multi-dimensional parallelism, where computational loads are split across various accelerators such as GPU clusters.…

Admission control is a key component in multimedia servers, which will allow the resources to be used by the client only when they are available. A problem faced by numerous content serving machines is overload, when there are too many…

Programming with replicated objects is difficult. Developers must face the fundamental trade-off between consistency and performance head on, while struggling with the complexity of distributed storage stacks. We introduce Correctables, a…

Real-time object detectors like YOLO achieve exceptional performance when trained on large datasets for multiple epochs. However, in real-world scenarios where data arrives incrementally, neural networks suffer from catastrophic forgetting,…

To increase performance and efficiency, systems use FPGAs as reconfigurable accelerators. A key challenge in designing these systems is partitioning computation between processors and an FPGA. An appropriate division of labor may be…

Data streaming relies on continuous queries to process unbounded streams of data in a real-time fashion. It is commonly demanding in computation capacity, given that the relevant applications involve very large volumes of data. Data…

Due to its high performance and decreasing cost per bit, flash is becoming the main storage medium in datacenters for hot data. However, flash endurance is a perpetual problem, and due to technology trends, subsequent generations of flash…

The key premise of federated learning (FL) is to train ML models across a diverse set of data-owners (clients), without exchanging local data. An overarching challenge to this date is client heterogeneity, which may arise not only from…

Checkpointing large amounts of related data concurrently to stable storage is a common I/O pattern of many HPC applications. However, such a pattern frequently leads to I/O bottlenecks that lead to poor scalability and performance. As…

Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and learning has attracted widespread attention as a new decentralized learning pattern. However, traditional consensus…

Generative models have achieved remarkable success across various applications, driving the demand for multi-GPU computing. Inter-GPU communication becomes a bottleneck in multi-GPU computing systems, particularly on consumer-grade GPUs. By…