Related papers: fabric-lib: RDMA Point-to-Point Communication for …

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet…

Large-scale LLM training requires collective communication libraries to exchange data among distributed GPUs. As a company dedicated to building and operating large-scale GPU training clusters, we encounter several challenges when using…

Emerging intelligent service scenarios in 6G communication impose stringent requirements for low latency, high reliability, and privacy preservation. Generative large language models (LLMs) are gradually becoming key enablers for the…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimizations, and stateful workloads such as reasoning, agents, and RL rollouts. Simulation is…

The efficient distributed training of Large Language Models (LLMs) is severely hampered by the extreme variance in context lengths. This data heterogeneity, amplified by conventional packing strategies and asymmetric forward-backward costs,…

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not…

Digital computing-in-memory (DCIM) has emerged as a promising solution for large language model (LLM) acceleration by minimizing data transfers between external DRAM and on-chip accelerators while maintaining high precision for superior…

This paper presents an integrated framework that combines traditional network optimization models with large language models (LLMs) to deliver interactive, explainable, and role-aware decision support for supply chain planning. The proposed…

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often…

This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity approaches are often heavy or slow for modern LLMs. LM-Fix runs a short test-vector pass and…

The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now scaling to trillions of parameters, has necessitated training across thousands of GPUs using complex hybrid parallelism strategies (e.g.,…

Fashion content generation is an emerging area at the intersection of artificial intelligence and creative design, with applications ranging from virtual try-on to culturally diverse design prototyping. Existing methods often struggle with…

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal…

Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks, especially in reasoning, a cornerstone for achieving Artificial General Intelligence (AGI).…

Efficiently deploying large language models (LLMs) in real-world scenarios remains a critical challenge, primarily due to hardware heterogeneity, inference framework limitations, and workload complexities.Efficiently deploying large…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

Various layer-skipping methods have been proposed to accelerate token generation in large language models (LLMs). However, limited attention has been paid to a fundamental question: How do computational demands vary across the generation of…

Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interaction. However, there is still a lack of exploration on how…