Related papers: Prefill vs. Decode Bottlenecks: SRAM-Frequency Tra…

Large Language Models (LLMs) have resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput has emerged as a key metric that…

Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This…

An effective way to improve energy efficiency is to throttle hardware resources to meet a certain performance target, specified as a QoS constraint, associated with all applications running on a multicore system. Prior art has proposed…

Scale is often attributed as one of the factors that cause an increase in the performance of LLMs, resulting in models with billion and trillion parameters. One of the limitations of such large models is the high computational requirements…

Large Language Models (LLMs) inference is central to modern AI applications, dominating worldwide datacenter workloads, making it critical to predict its energy footprint. Existing approaches estimate energy consumption as a simple linear…

The increasing size of large language models (LLMs) has led to a surge in memory requirements during training, often exceeding the capacity of high-bandwidth memory (HBM). Swap-based memory optimization incurs neither accuracy loss nor…

Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several…

Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by verifying multiple tokens within a single forward pass, which…

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource…

Fine-tuning is the process of adapting the pre-trained large language models (LLMs) for downstream tasks. Due to substantial parameters, fine-tuning LLMs on mobile devices demands considerable memory resources, and suffers from high…

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…

The extremely high computational and storage demands of large language models have excluded most edge devices, which were widely used for efficient machine learning, from being viable options. A typical edge device usually only has 4GB of…

To mitigate the ever-worsening Power Wall problem, more and more applications need to expand their power supply to the wide-voltage range including the near-threshold region. However, the read delay distribution of the SRAM cells under the…

Complex applications running on multicore processors show a rich performance phenomenology. The growing number of cores per ccNUMA domain complicates performance analysis of memory-bound code since system noise, load imbalance, or…

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high…

Conventional LLM inference architectures suffer from high energy and latency due to frequent data movement across memory hierarchies. We propose Ouroboros, a wafer-scale SRAM-based Computing-in-Memory (CIM) architecture that executes all…

Even in the era of Deep Learning based methods, traditional machine learning methods with large data sets continue to attract significant attention. However, we find an apparent lack of a detailed performance characterization of these…

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill…

In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile…

A large language model (LLM) is one of the most important emerging machine learning applications nowadays. However, due to its huge model size and runtime increase of the memory footprint, LLM inferences suffer from the lack of memory…