Related papers: MoLink: Distributed and Efficient Serving Framewor…

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM), which eliminates prefill-decoding interference and optimizes resource allocation. However, it is…

Generative AI like the Large Language Models (LLMs) has become more available for the general consumer in recent years. Publicly available services, e.g., ChatGPT, perform token generation on networked cloud server hardware, effectively…

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…

Large language models (LLMs) based on transformers have made significant strides in recent years, the success of which is driven by scaling up their model size. Despite their high algorithmic performance, the computational and memory…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Large models have achieved remarkable performance across a range of reasoning and understanding tasks. Prior work often utilizes model ensembles or multi-agent systems to collaboratively generate responses, effectively operating in a…

Serving generative inference of the large language model is a crucial component of contemporary AI applications. This paper focuses on deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial…

Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs…

Recent developments in large language models (LLMs) have demonstrated their remarkable proficiency in a range of tasks. Compared to in-house homogeneous GPU clusters, deploying LLMs in cloud environments with diverse types of GPUs is…

The recent surge of open-source large language models (LLMs) enables developers to create AI-based solutions while maintaining control over aspects such as privacy and compliance, thereby providing governance and ownership of the model…

Large language model (LLM) services are mostly centralized, leading to scalability bottlenecks and underutilization of substantial scattered GPU resources. While decentralization offers a promising alternative, existing frameworks primarily…

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…

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve…

In this paper, we consider a mixed-prompt scenario for a large language model (LLM) inference serving system that supports diverse applications with both short prompts and long prompts and heterogeneous SLOs for iteration time. To improve…

Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are proprietary LLMs like GPT-4 and GPT-o1, which have captured…

In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving…

Serving large language models (LLMs) for massive users is challenged by the significant memory footprint of the transient state, known as the key-value (KV) cache, which scales with sequence length and number of requests. Instead of renting…

GPUs have limited memory and it is difficult to train wide and/or deep models that cause the training process to go out of memory. It is shown in this paper how an open source tool called Large Model Support (LMS) can utilize a high…

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE…