Related papers: SpecInF: Exploiting Idle GPU Resources in Distribu…

Large Language Models (LLMs) have achieved remarkable success across many applications, with Mixture of Experts (MoE) models demonstrating great potential. Compared to traditional dense models, MoEs achieve better performance with less…

Recent advancements in Mixture of Experts (MoE) models have significantly increased their parameter scale as well as model performance. Extensive offloading techniques have been proposed to address the GPU memory limitations of MoE…

Continuous learning (CL) has emerged as one of the most popular deep learning paradigms deployed in modern cloud GPUs. Specifically, CL has the capability to continuously update the model parameters (through model retraining) and use the…

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

The demand for large language model inference is rapidly increasing. Pipeline parallelism offers a cost-effective deployment strategy for distributed inference but suffers from high service latency. While incorporating speculative decoding…

We devise a performance model for GPU training of Deep Learning Recommendation Models (DLRM), whose GPU utilization is low compared to other well-optimized CV and NLP models. We show that both the device active time (the sum of kernel…

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to…

This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research interest in recent years. SD is introduced as an innovative…

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage…

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

With the continuous advancement in the performance of large language models (LLMs), their demand for computational resources and memory has significantly increased, which poses major challenges for efficient inference on consumer-grade…

Large-scale GPU clusters are widely-used to speed up both latency-critical (online) and best-effort (offline) deep learning (DL) workloads. However, most DL clusters either dedicate each GPU to one workload or share workloads in time,…

As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…

Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…

Sizing a GPU fleet for LLM inference is harder than it looks. The obvious questions -- how many GPUs, which type, where to split a two-pool fleet -- have no closed-form answers. They depend on the full token-length distribution, the routing…

We present SPDL (Scalable and Performant Data Loading), an open-source, framework-agnostic library designed for efficiently loading array data to GPU. Data loading is often a bottleneck in AI applications, and is challenging to optimize…

First-come first-serve scheduling can result in substantial (up to 10%) of transiently idle nodes on supercomputers. Recognizing that such unfilled nodes are well-suited for deep neural network (DNN) training, due to the flexible nature of…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

Graph neural network (GNN) has been demonstrated to be a powerful model in many domains for its effectiveness in learning over graphs. To scale GNN training for large graphs, a widely adopted approach is distributed training which…

The rapid evolution and widespread adoption of generative large language models (LLMs) have made them a pivotal workload in various applications. Today, LLM inference clusters receive a large number of queries with strict Service Level…