paper-with-me

Papers

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models

2024-06-03 · Abhimanyu Bambhaniya, Ritik Raj, Geonhwa Jeong, Souvik Kundu, Sudarshan Srinivasan, Suvinay Subramanian, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna

Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these gigantic models efficiently for diverse inference use cases requires carefully designed hardware platforms with ample computing, memory, and network resources. With constant innovation in LLM serving optimizations and model architecture evolving at breakneck speed, the hardware requirements to meet Service Level Objectives (SLOs) remain an open research question. To answer the question, we present an analytical tool, GenZ, to efficiently navigate the relationship between diverse LLM model architectures(Dense, GQA, MoE, Mamba), LLM serving optimizations(Chunking, Speculative decoding, quanitization), and AI platform design parameters. Our tool estimates LLM inference performance metrics for the given scenario. We have validated against real hardware platforms running various different LLM models, achieving a max geomean error of 5.82.We use GenZ to identify compute, memory capacity, memory bandwidth, network latency, and network bandwidth requirements across diverse LLM inference use cases. We also study diverse architectural choices in use today (inspired by LLM serving platforms from several vendors) to help inform computer architects designing next-generation AI hardware accelerators and platforms. The trends and insights derived from GenZ can guide AI engineers deploying LLMs as well as computer architects designing next-generation hardware accelerators and platforms. Ultimately, this work sheds light on the platform design considerations for unlocking the full potential of large language models across a spectrum of applications. The source code is available at https://github.com/abhibambhaniya/GenZ-LLM-Analyzer . Users can also be tried it on at https://genz-llm-analyzer.streamlit.app/ without any setup on your web browser.

📄 PDF Abstract BibTeX arXiv:2406.01698

Code (1)

abhibambhaniya/genz-llm-analyzer 공식 구현

Tasks

ChunkingMambaNavigate

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
Attention 설명 없음
MoE 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis

2018-02-26 · Tal Ben-Nun, Torsten Hoefler

Deep Neural Networks (DNNs) are becoming an important tool in modern computing applications. Accelerating their training is a major challenge and techniques range from distributed algorithms to low-level circuit design. …

Deep LearningNeural Architecture SearchStochastic Optimization

A Modular Platform For Collaborative, Distributed Sensor Fusion

2023-03-13 · R. Spencer Hallyburton, Nate Zelter, David Hunt, Kristen Angell 외

Leading autonomous vehicle (AV) platforms and testing infrastructures are, unfortunately, proprietary and closed-source. Thus, it is difficult to evaluate how well safety-critical AVs perform and how safe they truly are.…

Sensor Fusion

Towards Demystifying Serverless Machine Learning Training

2021-05-17 · Jiawei Jiang, Shaoduo Gan, Yue Liu, Fanlin Wang 외

The appeal of serverless (FaaS) has triggered a growing interest on how to use it in data-intensive applications such as ETL, query processing, or machine learning (ML). Several systems exist for training large-scale ML …

BIG-bench Machine Learning

Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference

2026-02-17 · Pragya Sharma, Hang Qiu, Mani Srivastava arxiv

The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time …

Autonomous Driving

Guardians of the Deep Fog: Failure-Resilient DNN Inference from Edge to Cloud

2019-09-03 · Ashkan Yousefpour, Siddartha Devic, Brian Q. Nguyen, Aboudy Kreidieh 외

Partitioning and distributing deep neural networks (DNNs) over physical nodes such as edge, fog, or cloud nodes, could enhance sensor fusion, and reduce bandwidth and inference latency. However, when a DNN is distributed…

Distributed ComputingSensor Fusion