Related papers: Improving Instruction Fetch Efficiency via High-Le…

Rapid launch of thousands of jobs is essential for effective interactive supercomputing, big data analysis, and AI algorithm development. Achieving thousands of launches per second has required hardware to be available to receive these…

Accurate structural relaxation is critical for advanced materials design. Traditional approaches built on physics-derived first-principles calculations are computationally expensive, motivating the creation of machine-learning interatomic…

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1)…

Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many…

Modern storage systems intensively utilize data prefetching algorithms while processing sequences of the read requests. Performance of the prefetching algorithm (for instance increase of the cache hit ratio of the cache system - CHR)…

In this paper, we present iPrescribe, a scalable low-latency architecture for recommending 'next-best-offers' in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different…

A distributed heap storage manager has been implemented on the Fujitsu AP1000 multicomputer. The performance of various pre-fetching strategies is experimentally compared. Subjective programming benefits and objective performance benefits…

In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The…

Motivated by the increasing popularity of learning and predicting human user behavior in communication and computing systems, in this paper, we investigate the fundamental benefit of predictive scheduling, i.e., predicting and pre-serving…

The aim of parallel computing is to increase an application performance by executing the application on multiple processors. OpenMP is an API that supports multi platform shared memory programming model and shared-memory programs are…

The scaling of transformer-based Large Language Models (LLMs) has significantly expanded their context lengths, enabling applications where inputs exceed 100K tokens. Our analysis of a recent Azure LLM inference trace reveals a highly…

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which…

Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as catastrophic forgetting. Existing methods mitigate this by modifying the fine-tuning…

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

Web crawl is a main source of large language models' (LLMs) pretraining data, but the majority of crawled web pages are discarded in pretraining due to low data quality. This paper presents Craw4LLM, an efficient web crawling method that…

In a busy city street, a pedestrian surrounded by distractions can pick out a single sign if it is relevant to their route. Artificial agents in outdoor Vision-and-Language Navigation (VLN) are also confronted with detecting supervisory…

Hitherto discovered approaches analyze the execution time of a real time application on all the possible cache hierarchy setups to find the application specific optimal two level inclusive data cache hierarchy to reduce cost, space and…

Large-scale neural networks have demonstrated remarkable performance in different domains like vision and language processing, although at the cost of massive computation resources. As illustrated by compression literature, structural model…

Recent interpretability work has identified model-internal handles on post-trained behavior, including refusal directions, assistant/persona axes, and sparse chat-tuning features. These results localize where behaviors can be read out or…

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…