Related papers: Supporting Superpages and Lightweight Page Migrati…
It is important to design compact language models for efficient deployment. We improve upon recent advances in both the language modeling domain and the model-compression domain to construct parameter and computation efficient language…
We present a distributed data structure, which we call the rainbow skip graph. To our knowledge, this is the first peer-to-peer data structure that simultaneously achieves high fault tolerance, constant-sized nodes, and fast update and…
In this paper we present an algorithm-hardware codesign for camera-based autonomous flight in small drones. We show that the large write-latency and write-energy for nonvolatile memory (NVM) based embedded systems makes them unsuitable for…
We present MELODI, a novel memory architecture designed to efficiently process long documents using short context windows. The key principle behind MELODI is to represent short-term and long-term memory as a hierarchical compression scheme…
The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer…
Hybrid switching - in which a high bandwidth circuit switch (optical or wireless) is used in conjunction with a low bandwidth packet switch - is a promising alternative to interconnect servers in today's large scale data-centers. Circuit…
Many high end and next generation computing systems to incorporated alternative memory technologies to meet performance goals. Since these technologies present distinct advantages and tradeoffs compared to conventional DDR* SDRAM, such as…
Cloud resource management is often modeled by two-dimensional bin packing with a set of items that correspond to tasks having fixed CPU and memory requirements. However, applications running in clouds are much more flexible: modern…
The computational and memory challenges of large language models (LLMs) have sparked several optimization approaches towards their efficient implementation. While prior LLM-targeted quantization, and prior works on sparse acceleration have…
Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…
Application virtual memory footprints are growing rapidly in all systems from servers down to smartphones. To address this growing demand, system integrators are incorporating ever larger amounts of main memory, warranting rethinking of…
Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying…
Modern AI workloads such as large language models (LLMs) and retrieval-augmented generation (RAG) impose severe demands on memory, communication bandwidth, and resource flexibility. Traditional GPU-centric architectures struggle to scale…
Image bitmaps have been widely used in in-memory applications, which consume lots of storage space and energy. Compared with legacy DRAM, non-volatile memories (NVMs) are suitable for bitmap storage due to the salient features in capacity…
Emergency communications networks require in-network intelligence for timely traffic handling under dynamic demands and runtime constraints. In these environments, packets may need different inference behaviors, and conventional model…
Various state-of-the-art automated reasoning (AR) tools are widely used as backend tools in research of knowledge representation and reasoning as well as in industrial applications. In testing and verification, those tools often run…
The increasing size and complexity of modern deep neural networks (DNNs) pose significant challenges for on-device inference on mobile GPUs, with limited memory and computational resources. Existing DNN acceleration frameworks primarily…
Efficient load balancing is crucial in cloud computing environments to ensure optimal resource utilization, minimize response times, and prevent server overload. Traditional load balancing algorithms, such as round-robin or least…
Sparse Matrix-Vector Multiplication (SpMV) is the cornerstone in many iterative workloads, including large-scale graph analytics and sparse iterative solvers. Accelerating SpMV on real-world graphs remains challenging due to highly…
Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external storage require complex management and incur storage overhead,…