Related papers: PipeMax: Enhancing Offline LLM Inference on Commod…

The occurrence of bubbles in pipeline parallelism is an inherent limitation that can account for more than 40% of the large language model (LLM) training time and is one of the main reasons for the underutilization of GPU resources in LLM…

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from…

Efficient LLM inference is critical for real-world applications, especially within heterogeneous GPU clusters commonly found in organizations and on-premise datacenters as GPU architecture rapidly evolves. Current disaggregated prefill…

Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks in industry. Many of these tasks are performed in large batches or even offline, and the performance indicator…

This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to formulate inference computation of LLMs over heterogeneous…

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

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…

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…

Transformer-based large language models (LLMs) demonstrate impressive performance in long context generation. Extending the context length has disproportionately shifted the memory footprint of LLMs during inference to the key-value cache…

It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an…

Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance…

Efficient LLM serving must balance throughput and latency across diverse, bursty workloads. We introduce StreamServe, a disaggregated prefill decode serving architecture that combines metric aware routing across compute lanes with adaptive…

Transformers and LLMs have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is slow and often takes in the order…

As machine learning techniques are applied to a widening range of applications, high throughput machine learning (ML) inference servers have become critical for online service applications. Such ML inference servers pose two challenges:…

Modern LLM serving now spans multi-stage pipelines including RAG retrieval and KV cache reuse, each with distinct compute, memory, and latency demands. Inference engines expose a large configuration space with no systematic navigation…

Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall…

Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and synchronization delays in traditional model parallelism…

Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…