Related papers: Jenga: Effective Memory Management for Serving LLM…

Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…

Reducing the key-value (KV) cache size is a crucial step toward enabling efficient inference in large language models (LLMs), especially under latency and memory constraints. While Multi-Head Attention (MHA) offers strong representational…

Efficiently deploying large language models (LLMs) in real-world scenarios remains a critical challenge, primarily due to hardware heterogeneity, inference framework limitations, and workload complexities.Efficiently deploying large…

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput,…

Nowadays, many companies possess various types of AI accelerators, forming heterogeneous clusters. Efficiently leveraging these clusters for high-throughput large language model (LLM) inference services can significantly reduce costs and…

The rising computational and energy demands of deep learning, particularly in large-scale architectures such as foundation models and large language models (LLMs), pose significant challenges to sustainability. Traditional gradient-based…

The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to…

Large Language Models (LLMs) are increasingly deployed in production, contributing towards shifting the burden in terms of computational resources and energy demands from training to inference. While prior work has examined the energy cost…

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…

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

Deploying million-token Large Language Models (LLMs) is challenging because production workloads are highly heterogeneous, mixing short queries and long documents. This heterogeneity, combined with the quadratic complexity of attention,…

Retrieval-Augmented Generation (RAG) systems combine vector similarity search with large language models (LLMs) to deliver accurate, context-aware responses. However, co-locating the vector retriever and the LLM on shared GPU infrastructure…

The increasing adoption of large language models (LLMs) on heterogeneous computing platforms poses significant challenges to achieving high inference efficiency. To address these efficiency bottlenecks across diverse platforms, this paper…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

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…

The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when fine-tuning extensive prompt sequences. Current open-source…

As large language models (LLMs) continue to scale and new GPUs are released even more frequently, there is an increasing demand for LLM post-training in heterogeneous environments to fully leverage underutilized mid-range or…

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…