Related papers: Ascendra: Dynamic Request Prioritization for Effic…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level…

Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank…

The expanding context windows in large language models (LLMs) have greatly enhanced their capabilities in various applications, but they also introduce significant challenges in maintaining low latency, particularly in Time to First Token…

This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…

We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion. Specifically,…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods…

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct…

Large Language Models (LLMs) play a critical role in emerging agentic applications, where the timely completion of each entire inference is critical. Meanwhile, agentic LLM inferences are increasingly served on heterogeneous GPUs in…

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver…

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based…

Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve…

Agentic workflows carry out complex tasks by orchestrating multiple large language models (LLMs) and tools. Serving such workflows at a target throughput with low latency is challenging because they can be defined using arbitrary agentic…

Recent advances in AudioLLMs have enabled spoken dialogue systems to move beyond turn-based interaction toward real-time full-duplex communication, where the agent must decide when to speak, yield, or interrupt while the user is still…

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by…

Efficient scheduling of LLM inference tasks is essential for achieving low latency and high throughput, particularly with the growing use of reasoning-capable LLMs. Traditional strategies like First-Come-First-Serve (FCFS) often suffer from…

We have reached a practical and realistic phase in human-support dialogue agents by developing a large language model (LLM). However, when requiring expert knowledge or anticipating the utterance content using the massive size of the…

Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain…

Distributed prefix caching has become a core technique for efficient LLM serving. However, for long-context requests with high cache hit ratios, retrieving reusable KVCache blocks from remote servers has emerged as a new performance…