Related papers: Optimizing Long-context LLM Serving via Fine-grain…

Split learning (SL) has been recently proposed as a way to enable resource-constrained devices to train multi-parameter neural networks (NNs) and participate in federated learning (FL). In a nutshell, SL splits the NN model into parts, and…

In this work we propose an efficient parallelization of multiple-precision Taylor series method with variable stepsize and fixed order. For given level of accuracy the optimal variable stepsize determines higher order of the method than in…

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose…

As the context limits of Large Language Models (LLMs) increase, the range of possible applications and downstream functions broadens. In many real-world tasks, decisions depend on details scattered across collections of often disparate…

Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.…

In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application. The key components of Triple M are: 1) A sequence-to-sequence model adopts a novel multi-guidance…

Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct branches explore equivalent reasoning paths. We introduce…

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

Deploying deep learning (DL) models across multiple compute devices to train large and complex models continues to grow in importance because of the demand for faster and more frequent training. Data parallelism (DP) is the most widely used…

In recent years, long short-term memory neural networks (LSTMs) have been applied quite successfully to problems in handwritten text recognition. However, their strength is more located in handling sequences of variable length than in…

In this paper, we consider hybrid parallelism -- a paradigm that employs both Data Parallelism (DP) and Model Parallelism (MP) -- to scale distributed training of large recommendation models. We propose a compression framework called…

Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…

Generative Artificial Intelligence (GAI) is taking the world by storm with its unparalleled content creation ability. Large Language Models (LLMs) are at the forefront of this movement. However, the significant resource demands of LLMs…

Large Vision-Language Models (VLMs) face an inherent contradiction in image captioning: their powerful single-step generation capabilities often lead to a myopic decision-making process. This makes it difficult to maintain global narrative…

Parallel trajectory optimization via the Alternating Direction Method of Multipliers (ADMM) has emerged as a scalable approach to long-horizon motion planning. However, existing frameworks typically decompose the problem into parallel…

Distributed LLM inference requires careful coordination of parallelization strategies across hundreds to thousands of NPUs to meet production SLOs. Current systems like Megatron-LM rely on static heuristics that separately configure…

Bulk synchronous parallel (BSP) is the de-facto paradigm for distributed DNN training in today's production clusters. However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks…

Contrastive Decoding (CD) enhances the generation quality of large language models (LLMs) but incurs significant additional computational overhead due to the need for an auxiliary model. Existing internal self-contrastive decoding methods,…

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length,…

The past few years have witnessed growth in the computational requirements for training deep convolutional neural networks. Current approaches parallelize training onto multiple devices by applying a single parallelization strategy (e.g.,…