Related papers: Efficient Multi-Adapter LLM Serving via Cross-Mode…
Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially on consumer-grade hardware. Mixture of Experts (MoE) models provide an efficient…
Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy,…
Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension,…
Large language models (LLMs) are increasingly being deployed on mobile devices, but the limited DRAM capacity constrains the deployable model size. This paper introduces ActiveFlow, the first LLM inference framework that can achieve…
Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…
As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the quality and efficiency of the LLM post-training phase-including fine-tuning and inference,…
Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks in industry. Many of these tasks are performed in large batches or even offline, and the performance indicator…
Recently, there has been a demand to deploy Large Language Models (LLMs) on personal devices such as laptops and smartphones. These LLMs have different model variants when handling different tasks. However, personal devices have limited…
Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource-constrained settings. Despite recent effort on improving…
Finetuned LLMs often exhibit poor uncertainty quantification, manifesting as overconfidence, poor calibration, and unreliable prediction results on test data or out-of-distribution samples. One approach commonly used in vision for…
The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…
Spatio-temporal forecasting plays a crucial role in various sectors such as transportation systems, logistics, and supply chain management. However, existing methods are limited by their ability to handle large, complex datasets. To…
Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently. While prior work has…
High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…
KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…
Low-rank adaptation (LoRA) enables parameter efficient specialization of large language models (LLMs) through modular adapters, resulting in rapidly growing public adapter pools spanning diverse tasks. Effectively using these adapters…
Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…
Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…
In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…
Federated fine-tuning has emerged as a promising approach to adapt foundation models to downstream tasks using decentralized data. However, real-world deployment remains challenging due to the high computational and communication demands of…