Related papers: Supporting Superpages and Lightweight Page Migrati…
As deep learning models continue to increase in size, the memory requirements for training have surged. While high-level techniques like offloading, recomputation, and compression can alleviate memory pressure, they also introduce…
The cost of moving data between the memory units and the compute units is a major contributor to the execution time and energy consumption of modern workloads in computing systems. At the same time, we are witnessing an enormous amount of…
In today's data-sensitive landscape, distributed learning emerges as a vital tool, not only fortifying privacy measures but also streamlining computational operations. This becomes especially crucial within fully decentralized…
We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval-Augmented Generation (GraphRAG) in enterprise environments. While GraphRAG has shown promise for multi- hop reasoning and structured retrieval, its…
Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks. However, the massive size of these models poses huge challenges for their deployment in real-world…
In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism,…
Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…
Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning…
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…
Resilience is a major design goal for HPC. Checkpoint is the most common method to enable resilient HPC. Checkpoint periodically saves critical data objects to non-volatile storage to enable data persistence. However, using checkpoint, we…
Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…
Software-managed heterogeneous memory (HM) provides a promising solution to increase memory capacity and cost efficiency. However, to release the performance potential of HM, we face a problem of data management. Given an application with…
Data management systems have traditionally been designed to support either long-running analytics queries or short-lived transactions, but an increasing number of applications need both. For example, online games, socio-mobile apps, and…
Event camera-based pattern recognition is a newly arising research topic in recent years. Current researchers usually transform the event streams into images, graphs, or voxels, and adopt deep neural networks for event-based classification.…
Serverless computing is an emerging cloud paradigm that offers an elastic and scalable allocation of computing resources with pay-as-you-go billing. In the Function-as-a-Service (FaaS) programming model, applications comprise short-lived…
Network function virtualization (NFV) enhances service flexibility by decoupling network functions from dedicated hardware. To handle time-varying traffic in NFV network, virtualized network function (VNF) migration has been involved to…
PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation -- a phenomenon that crippled the batch size (and consequently…
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation and policy optimization dynamics: (i) uniform rollout…
This work presents a new method for unsupervised thermal image classification and semantic segmentation by transferring knowledge from the RGB domain using a multi-domain attention network. Our method does not require any thermal…
As DRAM and other transistor-based memory technologies approach their scalability limits, alternative storage solutions like Phase-Change Memory (PCM) are gaining attention for their scalability, fast access times, and zero leakage power.…