Related papers: Efficient Expression Templates for Operator Overlo…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

This article describes a very high-level language for clear description of distributed algorithms and optimizations necessary for generating efficient implementations. The language supports high-level control flows where complex…

Writing parallel codes is difficult and exhibits a fundamental trade-off between abstraction and performance. The high level language abstractions designed to simplify the complexities of parallelism make certain assumptions that impacts…

Code retrieval aims to provide users with desired code snippets based on users' natural language queries. With the development of deep learning technologies, adopting pre-trained models for this task has become mainstream. Considering the…

Transferring knowledge among various environments is important to efficiently learn multiple tasks online. Most existing methods directly use the previously learned models or previously learned optimal policies to learn new tasks. However,…

Spatio-temporal feature encoding is essential for encoding facial expression dynamics in video sequences. At test time, most spatio-temporal encoding methods assume that a temporally segmented sequence is fed to a learned model, which could…

This work aims to bridge the existing knowledge gap in the optimisation of latency-critical code, specifically focusing on high-frequency trading (HFT) systems. The research culminates in three main contributions: the creation of a…

[abridged] Context: Multidimensional arrays are used by many different algorithms. As such, indexing and broadcasting complex operations over multidimensional arrays are ubiquitous tasks and can be performance limiting. Inquiry:…

HPC systems employ a growing variety of compute accelerators with different architectures and from different vendors. Large scientific applications are required to run efficiently across these systems but need to retain a single code-base…

Regular expressions (regexes) are widely used in different fields of computer science, such as programming languages, string processing, and databases. However, existing tools for synthesizing or repairing regexes always assume that the…

Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel. A common way to build draft models, like EAGLE3 or DFlash is supervised…

Prompting is a mainstream paradigm for adapting large language models to specific natural language processing tasks without modifying internal parameters. Therefore, detailed supplementary knowledge needs to be integrated into external…

Automated text scoring (ATS) tasks, such as automated essay scoring and readability assessment, are important educational applications of natural language processing. Due to their interpretability of models and predictions, traditional…

The C++ programming language provides classes and structs as fundamental modeling entities. Consequently, C++ code tends to favour array-of-structs (AoS) for encoding data sequences, even though structure-of-arrays (SoA) yields better…

Optimizations in a traditional compiler are applied sequentially, with each optimization destructively modifying the program to produce a transformed program that is then passed to the next optimization. We present a new approach for…

Data quality and its effective selection are fundamental to improving the performance of machine translation models, serving as cornerstones for achieving robust and reliable translation systems. This paper presents a data selection…

Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is less effective for generative text-to-image models due to…

It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore,…

Efficient data selection is crucial to accelerate the pretraining of language model (LMs). While various methods have been proposed to enhance data efficiency, limited research has addressed the inherent conflicts between these approaches…

Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language…