Related papers: Beluga: A CXL-Based Memory Architecture for Scalab…

Recent advancements in neural network quantisation have yielded remarkable outcomes, with three-bit networks reaching state-of-the-art full-precision accuracy in complex tasks. These achievements present valuable opportunities for…

To cope with the increasing demand and computational intensity of deep neural networks (DNNs), industry and academia have turned to accelerator technologies. In particular, FPGAs have been shown to provide a good balance between performance…

The growing complexity of LLM usage today, e.g., multi-round conversation and retrieval-augmented generation (RAG), makes contextual states (i.e., KV cache) reusable across user requests. Given the capacity constraints of GPU memory, only a…

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a critical bottleneck. While Key-Value (KV) caching effectively…

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

In modern server CPUs, the Last-Level Cache (LLC) serves not only as a victim cache for higher-level private caches but also as a buffer for low-latency DMA transfers between CPU cores and I/O devices through Direct Cache Access (DCA).…

The Compute Express Link (CXL) is an open industry-standard interconnect between processors and devices such as accelerators, memory buffers, smart network interfaces, persistent memory, and solid-state drives. CXL offers coherency and…

Shared virtual memory (SVM) is key in heterogeneous systems on chip (SoCs), which combine a general-purpose host processor with a many-core accelerator, both for programmability and to avoid data duplication. However, SVM can bring a…

Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially on consumer-grade hardware. Mixture of Experts (MoE) models provide an efficient…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

This paper explores how Compute Express Link (CXL) can transform PCIe-based block storage into a scalable, byte-addressable working memory. We address the challenges of adapting block storage to CXL's memory-centric model by emphasizing…

Main memories play an important role in overall energy consumption of embedded systems. Using conventional memory technologies in future designs in nanoscale era causes a drastic increase in leakage power consumption and temperature-related…

Large language models (LLMs) rely on Key-Value (KV) cache to reduce time-to-first-token (TTFT) latency, but existing disk-based KV cache systems using file-per-object layouts suffer from severe scalability bottlenecks due to file system…

Computer systems are becoming increasingly heterogeneous with the emergence of new memory technologies and compute devices. GPUs alongside CPUs have become commonplace and CXL is poised to be a mainstay of cloud systems. The operating…

Running Large Language Models (LLMs) on edge devices is crucial for reducing latency, improving real-time processing, and enhancing privacy. By performing inference directly on the device, data does not need to be sent to the cloud,…

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused…

Recent Serverless workloads tend to be largescaled/CPU-memory intensive, such as DL, graph applications, that require dynamic memory-to-compute resources provisioning. Meanwhile, recent solutions seek to design page management strategies…