Related papers: HFX: Joint Design of Algorithms and Systems for Mu…

Recently, the number of off-the-shelf Large Language Models (LLMs) has exploded with many open-source options. This creates a diverse landscape regarding both serving options (e.g., inference on local hardware vs remote LLM APIs) and model…

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across…

The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on…

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…

Large language models (LLMs) have shown great progress in responding to user questions, allowing for a multitude of diverse applications. Yet, the quality of LLM outputs heavily depends on the prompt design, where a good prompt might enable…

In this report, we introduce Falcon-H1, a new series of large language models (LLMs) featuring hybrid architecture designs optimized for both high performance and efficiency across diverse use cases. Unlike earlier Falcon models built…

Serving numerous users and requests concurrently requires good fairness in Large Language Models (LLMs) serving system. This ensures that, at the same cost, the system can meet the Service Level Objectives (SLOs) of more users , such as…

Recent advances in large language models have facilitated the development of unified speech language models (SLMs) capable of supporting multiple speech tasks within a shared architecture. However, tasks such as automatic speech recognition…

Diffusion-based large language models (dLLMs) are trained flexibly to model extreme dependence in the data distribution; however, how to best utilize this information at inference time remains an open problem. In this work, we uncover an…

The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited…

Datacenters are witnessing a rapid surge in the adoption of serverless functions for microservices-based applications. A vast majority of these microservices typically span less than a second, have strict SLO requirements, and are chained…

Large language models (LLMs) are adopted for software and hardware design, yet these domains are still evaluated separately. Software benchmarks typically assume fixed hardware targets, while hardware benchmarks focus on component-level…

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…

As augmented large language models (LLMs) with external tools become increasingly popular in web applications, improving augmented LLM inference serving efficiency and optimizing service-level objectives (SLOs) are critical for enhancing…

Function calling is a fundamental capability of today's large language models, but sequential function calling posed efficiency problems. Recent studies have proposed to request function calls with parallelism support in order to alleviate…

Long-context supervised fine-tuning (Long-SFT) plays a vital role in enhancing the performance of large language models (LLMs) on long-context tasks. To smoothly adapt LLMs to long-context scenarios, this process typically entails training…

Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency.…

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…