相关论文: Re-enabling high-speed caching for LSM-trees

Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…

Log-Structured Merge tree (LSM tree) Key-Value (KV) stores have become a foundational layer in the storage stacks of datacenter and cloud services. Current approaches for achieving reliability and availability avoid replication at the KV…

We develop a dynamic dictionary data structure for the GPU, supporting fast insertions and deletions, based on the Log Structured Merge tree (LSM). Our implementation on an NVIDIA K40c GPU has an average update (insertion or deletion) rate…

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,…

Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single…

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. LLM inference systems, however, are slow compared to database systems, and inference performance and…

Large language models (LLMs) operate within fixed context windows that fundamentally limit conversational continuity. When context fills, compaction discards history irreversibly; when sessions end, all memory resets to zero. Existing…

Much sequential data exhibits highly non-uniform information distribution. This cannot be correctly modeled by traditional Long Short-Term Memory (LSTM). To address that, recent works have extended LSTM by adding more activations between…

Serving Large Language Models (LLMs) at scale requires meeting strict Service Level Objectives (SLOs) under severe computational and memory constraints. Nevertheless, traditional caching strategies fall short: exact-matching and prefix…

Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and privacy-preserving…

Being more powerful and intrusive into user-device interactions, LLMs are eager for on-device execution to better preserve user privacy. In this work, we propose a new paradigm of mobile AI: LLM as a system service on mobile devices…

Although Large Language Models (LLMs) have demonstrated remarkable capabilities, their massive parameter counts and associated extensive computing make LLMs' deployment the main part of carbon emission from nowadays AI applications.…

Large Language Model (LLM) cascade systems are designed to balance efficiency and performance by processing queries with lightweight models while selectively escalating complex cases to more powerful ones. Such systems seek to reduces…

Recently, neural networks have achieved great success on sentiment classification due to their ability to alleviate feature engineering. However, one of the remaining challenges is to model long texts in document-level sentiment…

As a result of RAM becoming cheaper, there has been a trend in key-value store design towards maintaining a fast in-memory index (such as a hash table) while logging user operations to disk, allowing high performance under failure-free…

On-device recommendation is critical for a number of real-world applications, especially in scenarios that have agreements on execution latency, user privacy, and robust functionality when internet connectivity is unstable or even…

The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and…

The use of low numerical precision is a fundamental optimization included in modern accelerators for Deep Neural Networks (DNNs). The number of bits of the numerical representation is set to the minimum precision that is able to retain…

Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynamic activations, and key-value caches. While static weights…

This paper presents new alternatives to the well-known Bloom filter data structure. The Bloom filter, a compact data structure supporting set insertion and membership queries, has found wide application in databases, storage systems, and…