Large language models (LLMs) are widely applied in chatbots, code generators, and search engines. Workload such as chain-of-throught, complex reasoning, agent services significantly increase the inference cost by invoke the model repeatedly. Optimization methods such as parallelism, compression, and caching have been adopted to reduce costs, but the diverse service requirements make it hard to select the right method. Recently, specialized LLM inference engines have emerged as a key component for integrating the optimization methods into service-oriented infrastructures. However, a systematic study on inference engines is still lacking.This paper provides a comprehensive evaluation of 25 open-source and commercial inference engines. We examine each inference engine in terms of ease-of-use, ease-of-deployment, general-purpose support, scalability, and suitability for throughput- and latency-aware computation. Furthermore, we explore the design goals of each inference engine by investigating the optimization techniques it supports. In addition, we assess the ecosystem maturity of open source inference engines and handle the performance and cost policy of commercial solutions.We outline future research directions that include support for complex LLM-based services, support of various hardware, and enhanced security, offering practical guidance to researchers and developers in selecting and designing optimized LLM inference engines. We also provide a public repository to continually track developments in this fast-evolving field: \href{https://github.com/sihyeong/Awesome-LLM-Inference-Engine}{https://github.com/sihyeong/Awesome-LLM-Inference-Engine}.

As data-intensive applications grow, batch processing in limited-resource environments faces scalability and resource management challenges. Serverless computing offers a flexible alternative, enabling dynamic resource allocation and automatic scaling. This paper explores how serverless architectures can make large-scale ML inference tasks faster and cost-effective by decomposing monolithic processes into parallel functions. Through a case study on sentiment analysis using the DistilBERT model and the IMDb dataset, we demonstrate that serverless parallel processing can reduce execution time by over 95% compared to monolithic approaches, at the same cost.

In recent years, Artificial Intelligence (AI) and Machine Learning (ML) have grown tremendously in popularity across various industries. From healthcare and finance to retail and automotive, adopting machine learning models has led to significant advancements[1]. However, building machine learning models traditionally requires deep knowledge in multiple areas, such as data preprocessing, feature engineering, model selection, hyperparameter tuning, and evaluation[2]. For many beginners and even experienced practitioners, this process can be time-consuming and technically challenging. This is where AutoML (Automated Machine Learning) comes in. AutoML simplifies the process of building machine learning models by automating many of the steps that would otherwise require manual intervention [3]. AutoML tools can automatically preprocess data, select the most suitable algorithms, and fine-tune hyperparameters to produce highly accurate models [4]. This automation not only speeds up the model development cycle but also allows users without deep knowledge of machine learning to create models with comparable performance to those made by experienced data scientists.

Recent surge in Large Language Model (LLM) availability has opened exciting avenues for research. However, efficiently interacting with these models presents a significant hurdle since LLMs often reside on proprietary or self-hosted API endpoints, each requiring custom code for interaction. Conducting comparative studies between different models can therefore be time-consuming and necessitate significant engineering effort, hindering research efficiency and reproducibility. To address these challenges, we present prompto, an open source Python library which facilitates asynchronous querying of LLM endpoints enabling researchers to interact with multiple LLMs concurrently, while maximising efficiency and utilising individual rate limits. Our library empowers researchers and developers to interact with LLMs more effectively and enabling faster experimentation and evaluation. prompto is released with an introductory video (https://youtu.be/-eZAmlV4ypk) under MIT License and is available via GitHub (https://github.com/alan-turing-institute/prompto).

In recent years, the rapid advancement of large-scale pre-trained language models based on transformer architectures has revolutionized natural language processing tasks. Among these, ChatGPT has gained widespread popularity, demonstrating human-level conversational abilities and attracting over 100 million monthly users by late 2022. Concurrently, Baidu's commercial deployment of the Ernie Wenxin model has significantly enhanced marketing effectiveness through AI-driven technologies. This paper focuses on optimizing high-performance inference for Ernie models, emphasizing GPU acceleration and leveraging the Paddle inference framework. We employ techniques such as Faster Transformer for efficient model processing, embedding layer pruning to reduce computational overhead, and FP16 half-precision inference for enhanced computational efficiency. Additionally, our approach integrates efficient data handling strategies using multi-process parallel processing to minimize latency. Experimental results demonstrate that our optimized solution achieves up to an 8.96x improvement in inference speed compared to standard methods, while maintaining competitive performance.

Despite remarkable advancements in emulating human-like behavior through Large Language Models (LLMs), current textual simulations do not adequately address the notion of time. To this end, we introduce TimeArena, a novel textual simulated environment that incorporates complex temporal dynamics and constraints that better reflect real-life planning scenarios. In TimeArena, agents are asked to complete multiple tasks as soon as possible, allowing for parallel processing to save time. We implement the dependency between actions, the time duration for each action, and the occupancy of the agent and the objects in the environment. TimeArena grounds to 30 real-world tasks in cooking, household activities, and laboratory work. We conduct extensive experiments with various state-of-the-art LLMs using TimeArena. Our findings reveal that even the most powerful models, e.g., GPT-4, still lag behind humans in effective multitasking, underscoring the need for enhanced temporal awareness in the development of language agents.

The hottest thing in technology is an unprepossessing sliver of silicon closely related to the chips that power video game graphics. It's an artificial intelligence chip, designed specifically to make building AI systems such as ChatGPT faster and cheaper. Such chips have suddenly taken center stage in what some experts consider an AI revolution that could reshape the technology sector -- and possibly the world along with it. Shares of Nvidia, the leading designer of AI chips, rocketed up almost 25% last Thursday after the company forecast a huge jump in revenue that analysts said indicated soaring sales of its products. The company was briefly worth more than $1 trillion on Tuesday.

The AI train has been gaining steam for several years now, and nothing appears ready to stop it (except for bad data, that is). With momentum building, which direction will AI head in 2023? We leave that to the experts. Many AI projects are ill-conceived and ultimately fail for that reason. In 2023, enterprises will find a new vigilance when it comes to assessing the efficacy of AI, says Zohar Bronfman, co-founder and CEO of Pecan AI. "In 2023, business leaders will evaluate potential data science projects much more rigorously than in the past. These projects often fail to generate real impact due to poor alignment with business needs or because they never make it into production. With the expense and time commitment involved in data science, leaders will scrutinize proposed efforts more carefully and investigate the right way to pursue them to ensure that business-improvement actions could be taken in the near term based on the output of the models -- or scuttle them before resources are wasted," Bronfman says.

Training of convolutional neural networks is a high dimensional and a non-convex optimization problem. At present, it is inefficient in situations where parametric learning rates can not be confidently set. Some past works have introduced Newton methods for training deep neural networks. Newton methods for convolutional neural networks involve complicated operations. Finding the Hessian matrix in second-order methods becomes very complex as we mainly use the finite differences method with the image data. Newton methods for convolutional neural networks deals with this by using the sub-sampled Hessian Newton methods. In this paper, we have used the complete data instead of the sub-sampled methods that only handle partial data at a time. Further, we have used parallel processing instead of serial processing in mini-batch computations. The results obtained using parallel processing in this study, outperform the time taken by the previous approach.

Gradual pattern mining allows for extraction of attribute correlations through gradual rules such as: "the more X, the more Y". Such correlations are useful in identifying and isolating relationships among the attributes that may not be obvious through quick scans on a data set. For instance, a researcher may apply gradual pattern mining to determine which attributes of a data set exhibit unfamiliar correlations in order to isolate them for deeper exploration or analysis. In this work, we propose an ant colony optimization technique which uses a popular probabilistic approach that mimics the behavior biological ants as they search for the shortest path to find food in order to solve combinatorial problems. In our second contribution, we extend an existing gradual pattern mining technique to allow for extraction of gradual patterns together with an approximated temporal lag between the affected gradual item sets. Such a pattern is referred to as a fuzzy-temporal gradual pattern and it may take the form: "the more X, the more Y, almost 3 months later". In our third contribution, we propose a data crossing model that allows for integration of mostly gradual pattern mining algorithm implementations into a Cloud platform. This contribution is motivated by the proliferation of IoT applications in almost every area of our society and this comes with provision of large-scale time-series data from different sources.