Related papers: Dynamic read & write optimization with TurtleKV

Modern mainstream persistent key-value storage engines utilize Log-Structured Merge tree (LSM-tree) based designs, optimizing read/write performance by leveraging sequential disk I/O. However, the advent of SSDs, with their significant…

The exponential growth of data-intensive applications has placed unprecedented demands on modern storage systems, necessitating dynamic and efficient optimization strategies. Traditional heuristics employed for storage performance…

We present~\emph{KV-Tandem}, a modular architecture for building LSM-based storage engines on top of simple, non-ordered persistent key-value stores (KVSs). KV-Tandem enables advanced functionalities such as range queries and snapshot…

As LLM reasoning performance plateau, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries. Prior approaches including length regularization, adaptive routing, and…

Auto-regressive inference of transformers benefit greatly from Key-Value (KV) caching, but can lead to major memory bottlenecks as model size, batch size, and sequence length grow at scale. We introduce Multi-Layer Key-Value (MLKV) sharing,…

We present a novel dynamic configuration technique for deep neural networks that permits step-wise energy-accuracy trade-offs during runtime. Our configuration technique adjusts the number of channels in the network dynamically depending on…

Preprocessing pipelines in deep learning aim to provide sufficient data throughput to keep the training processes busy. Maximizing resource utilization is becoming more challenging as the throughput of training processes increases with…

Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Continual learning remains a challenge across various natural language processing (NLP) tasks, as models updated with new training data often risk catastrophic forgetting of previously acquired knowledge. We introduce a discrete key-value…

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit…

Database Management Systems and K/V-Stores operate on updatable datasets -- massively exceeding the size of available main memory. Tree-based K/V storage management structures became particularly popular in storage engines. B+ Trees allow…

The Receptance Weighted Key Value (RWKV) model offers a novel alternative to the Transformer architecture, merging the benefits of recurrent and attention-based systems. Unlike conventional Transformers, which depend heavily on…

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

In Online Learning to Rank (OLTR) the aim is to find an optimal ranking model by interacting with users. When learning from user behavior, systems must interact with users while simultaneously learning from those interactions. Unlike other…

Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization. Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics and reducing the retention of…

LSM-tree is a widely adopted data structure in modern key-value store systems that optimizes write performance in write-heavy applications by using append writes to achieve sequential writes. However, the unpredictability of LSM-tree…

In Multi-Task Learning (MTL), it is a common practice to train multi-task networks by optimizing an objective function, which is a weighted average of the task-specific objective functions. Although the computational advantages of this…

Learned indexes have emerged as a promising alternative to traditional index structures, offering higher throughput and lower memory usage by approximating the cumulative key distribution function with lightweight models. Despite these…