Related papers: Efficient Multi-Adapter LLM Serving via Cross-Mode…

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR. The model consists of a big size common LM and small size adapters. The model can perform multi-domain adaptation with only the small size…

Across large language model (LLM) applications, we observe an emerging trend for reusing KV caches to save the prefill delays of processing repeated input texts in different LLM inputs. This has led to a broad design space, including…

As large language models (LLMs) grow in size, traditional full fine-tuning becomes increasingly impractical due to its high computational and storage costs. Although popular parameter-efficient fine-tuning methods, such as LoRA, have…

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited GPU memory. Existing solutions first proposed the…

Multi-agent systems increasingly orchestrate multiple specialized language models to solve complex real-world problems, often invoking them over a shared context. This execution pattern repeatedly processes the same prompt prefix across…

The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

Fine-tuning Large Language Models (LLMs) is a common practice to adapt pre-trained models for specific applications. While methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls…

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As…

Large Language Models (LLMs) have demonstrated remarkable fluency across a range of natural language tasks, yet remain vulnerable to hallucinations - factual inaccuracies that undermine trust in real world deployment. We present…

Time series modeling holds significant importance in many real-world applications and has been extensively studied. While pre-trained foundation models have made impressive strides in the fields of natural language processing (NLP) and…

LLM agents today communicate via text, which incurs considerable latency and information loss due to the need to autoregressively decode the sharer model's state and encode at the receiver model. Recent work such as Cache-to-Cache (C2C; Fu…

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…

Recent attempts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for multi-task adaptation of Large Language Models (LLMs) often replace whole attention/FFN layers with switch experts or append parallel expert branches,…

Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference. In this work, we embrace the idea of looping back to move…

This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…