2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Presenter: Haichen Shen, Yao Wang Amazon SageMaker Neo, Deep Engine Science Dynamic Model in TVM AWS AI© 2019, Amazon Web Services while loop Limitation of TVM/graph runtime ● Cannot compile and run dynamic models© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Support dynamic model in TVM ● Support Any-dim dispatch for a (sub-)graph In collaboration with Jared Roesch, Zhi Chen, Wei Chen© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. “Any” in Relay typing Any: represent an unknown

© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon/Intel Confidentia Presenter: Zhi Chen, Cody Yu Amazon SageMaker Neo, Deep Engine Science Bring Your Own Codegen to TVM TVM AWS AI© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Considering You... Design and manufacture a deep learning chip which achieves amazing performance on widely-used operators Suppression (NMS) is too new to be supported by your chip But NMS is supported by TVM!© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Let TVM Be the Compiler of Your Chip Your chip

© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Animesh Jain Amazon SageMaker Neo Compilation of Quantized Models in TVM AWS AI© 2019, Amazon Web Services, Inc. or its Affiliates 𝑟𝑒𝑎𝑙_𝑣𝑎𝑙𝑢𝑒 = 𝑠𝑐𝑎𝑙𝑒 ∗ (𝑞𝑢𝑎𝑛𝑡𝑖𝑧𝑒𝑑_𝑣𝑎𝑙𝑢𝑒 − 𝑧𝑒𝑟𝑜_𝑝𝑜𝑖𝑛𝑡)© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Quantization in TVM • Quantization within TVM pre-quantized graph in TFLite or MxNet • Use high-level wrapper ops of QNN dialect© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. TVM Overview Framework Graph Mxnet TF …. parsers

23 10/22 4/25 800MM Big Six* USA Technology Company CapEx *Apple, NVIDIA, Microsoft, Alphabet, Amazon (AWS only), & Meta Platforms Source: Capital IQ (3/25), Morgan Stanley 2014 2024 CapEx, $B +63% one can make. The magic of watching AI do your work for you feels like the early days of email and web search – technologies that fundamentally changed our world. The better / faster / cheaper impacts the installed based of smartphones & tablets in 2020. Cloud & data center capex includes Google, Amazon, Microsoft, Meta, Alibaba, Apple, IBM, Oracle, Tencent, & Baidu for ten years ending 2022. ‘Tens

© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Trademark Deploying GluonCV models using TVM© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Amazon Trademark Deploy GluonCV Models GluonCV Models MXNet Computational Graph Json Acyclic Graph Export As-is Optimize with TVM© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved reserved. Amazon Trademark Deploy GluonCV Models https://arxiv.org/pdf/1907.02154.pdf© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Trademark Overall Performance AWS

大模型训练平台与工具根据其性质不同，可分为以下几类： 这些平台提供了从模型开发到部署的综合解决方案，包括计算资源、 数据存储、模型训练和部署服务。它们通常提供易于使用的界面，支 持快速迭代和大规模部署。Amazon SageMaker、Google Cloud AI Platform 和 Microsoft Azure Machine Learning 都是提供端到 端机器学习服务的云平台。 这些工具 益于其简洁的语法、强大的库支持（如 ）和深度学习框架（如 ）。 此外， ，C++ 有时 用于优化计算密集型任务，而 Java 在企业环境中处理模型部署和系 统集成方面常见。JavaScript 适用于 Web 环境的 LLM 应用。 13 / 32 LLM 基础设施：编程语言 2023 年是大语言模型 (LLM) 之年，Python 作为人工智能领域使用度最高的编程语言，在 2023 年到底有多火？

evals How Morgan Stanley iterated to ensure quality and safety As a global leader in financial services, Morgan Stanley is a relationship business. Not surprisingly, there were some questions across Generative AI Solutions To find out more, watch Morgan Stanley: Shaping the Future of Financial Services and ask us about our Eval Frameworks. 7 AI in the EnterpriseEvals defined Evaluation is the process example of OpenAI’s agentic approach. Leveraging its own virtual browser, Operator can navigate the web, click on buttons, fill in forms, and gather data just like a human would. It can also run processes

conferenceCommunityOpen Source Community Open source: ~280 contributors from UW, Berkeley, Cornell, UCLA, Amazon, Huawei, NTT, Facebook, Microsoft, Qualcomm, Alibaba, Intel, … Incubated as Apache TVM recently

High Frequency & High Compute Efficiency ˃ Supported on U200 – 3 Instances U250 – 4 Instances Amazon F1 ˃ ~1536 DSPs @ 700MHz Execution Controller Spill / Restore DMA Controller Weights DMA Controller

点数，免费体验。 微软Azure https://ai.azure.com 671B（全量模型） 需注册微软账户并创建订阅，免费部署，支持参数调节。 亚马逊AWS https://aws.amazon.com/c n/blogs/aws/deepseek-r1- models-now-available-on- aws 671B（全量模型） 需注册AWS账户，填写付款方式，免费部署。 Cerebras