Related papers: LightCode: Compiling LLM Inference for Photonic-El…

LLM inference exhibits substantial variability across queries and execution phases, yet inference configurations are often applied uniformly. We present a measurement-driven characterization of workload heterogeneity and energy-performance…

With the recent advances in optical phase change material (PCM), photonic in-memory neurocomputing has demonstrated its superiority in optical neural network (ONN) designs with near-zero static power consumption, time-of-light latency, and…

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…

Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…

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…

Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges,…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

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…

Utilizing Large Language Models (LLMs) for complex tasks is challenging, often involving a time-consuming and uncontrollable prompt engineering process. This paper introduces a novel human-LLM interaction framework, Low-code LLM. It…

Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. However, the increasing size and complexity of LLMs present…

Major challenges in LLMs inference remain frequent memory bandwidth bottlenecks, computational redundancy, and inefficiencies in long-sequence processing. To address these issues, we propose LLM-CoOpt, a comprehensive algorithmhardware…

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text…

Context: Since it is well-established that developers spend a substantial portion of their time understanding source code, the ability to automatically identify algorithms within source code presents a valuable opportunity. This capability…

Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and…

Speculative decoding has emerged as a promising lossless approach for accelerating Large Language Models (LLMs). As reasoning LLMs increasingly suffer from decode-stage overhead and approximation-based methods degrade accuracy, lossless…

Modern tensor compilers such as TorchInductor deliver substantial speedups on mainstream models, yet face a systematic performance ceiling on long-tail workloads -- our profiling shows that 43% of real-world subgraphs experience end-to-end…

Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…

The edge computing paradigm has emerged to handle cloud computing issues such as scalability, security and low response time among others. This new computing trend heavily relies on ubiquitous embedded systems on the edge. Performance and…

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…

LLM-based applications have been widely used in various industries, but with the increasing of models size, an efficient large language model (LLM) inference system is an urgent problem to be solved for service providers. Since the…