Related papers: Inference without Interference: Disaggregate LLM I…
With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase…
Serving disaggregated large language models has been widely adopted in industrial practice for enhanced performance. However, too many tokens generated in decoding phase, i.e., occupying the resources for a long time, essentially hamper the…
On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably…
Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…
Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…
LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling…
This paper investigates the optimal allocation of large language model (LLM) inference workloads across heterogeneous edge data centers over time. Each data center features on-site renewable generation and faces dynamic electricity prices…
Large Language Model (LLM) inference is widely used in interactive assistants and agentic systems. In latency-sensitive deployments, inference time can become dominated by host-side overheads. Existing approaches typically expose this cost…
Large language models (LLMs) have achieved remarkable success across various artificial intelligence tasks. However, their enormous sizes and computational demands pose significant challenges for the deployment on edge devices. To address…
Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…
To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the…
Large language models (LLMs) have demonstrated remarkable success across various application domains, but their enormous sizes and computational demands pose significant challenges for deployment on resource-constrained edge devices. To…
Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…
Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…
Large Language Models (LLMs) are widely used in generative applications such as chatting, code generation, and reasoning. However, many realworld workloads such as classification, question answering, recommendation, and text embedding rely…
Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-prefill aggregation, to prefill-decode (P/D) disaggregation,…
Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low…
We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the…
Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge…
Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime…