Related papers: MetaHive: A Cache-Optimized Metadata Management fo…

In cost-sensitive deployments, RAID arrays may combine SSDs with different performance levels. Such heterogeneity arises when aging SSDs degrade yet remain usable, or when failed drives are replaced with new devices of explicitly better…

KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, are largely heuristic and lack dynamic budget allocation. To…

Cloud business intelligence is an increasingly popular choice to deliver decision support capabilities via elastic, pay-per-use resources. However, data security issues are one of the top concerns when dealing with sensitive data. In this…

Homomorphic encryption (HE) is a promising cryptographic technique for enabling secure collaborative machine learning in the cloud. However, support for homomorphic computation on ciphertexts under multiple keys is inefficient. Current…

This paper presents a novel approach to cloud storage challenges by integrating NextCloud, TrueNAS, and QEMU/KVM. Our research demonstrates how this combination creates a robust, flexible, and economical cloud storage system suitable for…

Transformer decoders have achieved strong results across tasks, but the memory required for the KV cache becomes prohibitive at long sequence lengths. Although Cross-layer KV Cache sharing (e.g., YOCO, CLA) offers a path to mitigate KV…

Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike…

Microservices architecture, known for its agility and efficiency, is an ideal framework for cloud-based software development and deployment. When integrated with containerization and orchestration systems, resource management becomes more…

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Existing Cross Modal Hashing (CMH) methods are mainly designed for balanced data, while imbalanced data with long-tail distribution is more general in real-world. Several long-tail hashing methods have been proposed but they can not adapt…

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead…

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression and eviction…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvement in offline video understanding. However, extending these capabilities to streaming video inputs, remains challenging, as existing…

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

In virtualized data centers, consolidation of Virtual Machines (VMs) on minimizing the number of total physical machines (PMs) has been recognized as a very efficient approach. This paper considers the energy-efficient consolidation of VMs…

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

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…

The memory demand of virtual machines (VMs) is increasing, while DRAM has limited capacity and high power consumption. Non-volatile memory (NVM) is an alternative to DRAM, but it has high latency and low bandwidth. We observe that the VM…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…