rights reserved. Presenter: Haichen Shen, Yao Wang Amazon SageMaker Neo, Deep Engine Science Dynamic Model in TVM AWS AI© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Models with models© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Support dynamic model in TVM ● Support Any-dim in typing ● Use shape function to compute the type at runtime ● Virtual or its Affiliates. All rights reserved. API Example input_name = "data" input_shape = [tvm.relay.Any(), 3, 224, 224] dtype = "float32" block = get_model('resnet50_v1', pretrained=True) mod, params

Efficient Mixture-of-Experts Language Model DeepSeek-AI research@deepseek.com Abstract We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models. The model checkpoints are available at h t t p s : / / g i t h u b . c o m / d e e p s e e k - a i / D e e p Work 21 A Contributions and Acknowledgments 27 B DeepSeek-V2-Lite: A 16B Model Equipped with MLA and DeepSeekMoE 29 2 B.1 Model Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

Change Happening Faster Than Ever? Yes, It Is • AI User + Usage + CapEx Growth = Unprecedented • AI Model Compute Costs High / Rising + Inference Costs Per Token Falling = Performance Converging + Developer 2/24 2/25 4/25 75% 60% 10% 21% 15% 0% Details on Page 293 USA – LLM #1 China USA – LLM #2 AI Model Compute Costs High / Rising + Inference Costs Per Token Falling = Performance Converging + Developer Change Happening Faster Than Ever? Yes, It Is • AI User + Usage + CapEx Growth = Unprecedented • AI Model Compute Costs High / Rising + Inference Costs Per Token Falling = Performance Converging + Developer

design foundations In its most fundamental form, an agent consists of three core components: 01 Model The LLM powering the agent’s reasoning and decision-making 02 Tools External functions or APIs the the workflow. Not every task requires the smartest model—a simple retrieval or intent classification task may be handled by a smaller, faster model, while harder tasks like deciding whether to approve approve a refund may benefit from a more capable model. An approach that works well is to build your agent prototype with the most capable model for every task to establish a performance baseline. From there

writing styles 59 For few-shot prompting with classification tasks, mix up the classes 59 Adapt to model updates 60 Experiment with output formats 60 JSON Repair 61 Working with Schemas 62 Experiment When thinking about a large language model input and output, a text prompt (sometimes accompanied by other modalities such as image prompts) is the input the model uses to predict a specific output. You can be complicated. Many aspects of your prompt affect its efficacy: the model you use, the model’s training data, the model configurations, your word-choice, style and tone, structure, and context

capabilities. Our Applied Team turns those models into products, like ChatGPT Enterprise and our API. And our Deployment Team takes these products into companies to address their most pressing use cases They started with three model evals: 01 Language translation Measuring the accuracy and quality of translations produced 
 by a model. 02 Summarization Evaluating how a model condenses information, using resilient to change. 
 Evals are built around tasks that measure 
 the quality of the output of a model against 
 a benchmark—is it more accurate? More compliant? Safer? Your key metrics will depend on

何静 能做什么？ 要怎么做？ 效果如何？ 一 能做什么？ 数据挖掘 数据分析 数据采集 数据处理 数据可视化 AIGC 数据应用 通过编写爬虫代码、访问数据库、读取文件、调用API等方式，采 集社交媒体数据、数据库内容、文本数据、接口数据等。 通过数据清洗、数据集成、数据变换、特征工程等方式，实 现数据纠错、数据整合、格式转换、特征提取等。 对数据进行诊断、预测、关联、聚类分析，常用于问题 Belk (2018). A universal material+testing machine(MTS System Corporation, Eden Prairie, MIN, USA, Model 661; Fig1,)was used to determine the shell strength. Each shell valve was placed horizontally with Belk (2018). A universal material-testing machine (MTS System Corporation, Eden Prairie, MN, USA, Model 661; Fig. 1) was used to determine the shell strength. Each shell valve was placed horizontally with

昆仑芯K200集群 企业级复杂任务推理 32B 壁彻算⼒平台+昇腾910B集群 科研计算与多模态处理 四、云端部署替代⽅案 1. 国内云服务商推荐 平台 核⼼优势 适⽤场景 硅基流动 官⽅推荐API，低延迟，⽀持多模态模型 企业级⾼并发推理 腾讯云 ⼀键部署+限时免费体验，⽀持VPC私有化 中⼩规模模型快速上线 PPIO派欧云 价格仅为OpenAI 1/20，注册赠5000万tokens 低成本尝鲜与测试 1. 成本警示： 70B模型：需3张以上80G显存显卡（如RTX A6000），单卡⽤户不可⾏。 671B模型：需8xH100集群，仅限超算中⼼部署。 2. 替代⽅案： 个⼈⽤户推荐使⽤云端API（如硅基流动），免运维且合规。 3. 国产硬件兼容性：需使⽤定制版框架（如昇腾CANN、沐曦MXMLLM）。 llama-gguf-split --merge DeepSeek-R1-UD-IQ1_M-00001-of-00004 chmod 600 /swapfile sudo mkswap /swapfile sudo swapon /swapfile 七、附录：技术⽀持与资源 华为昇腾：昇腾云服务 沐曦GPU：免费API体验 李锡涵博客：完整部署教程 结语 Deepseek R1 的本地化部署需极⾼的硬件投⼊与技术⻔槛，个⼈⽤户务必谨慎，企业⽤户应充 分评估需求与成本。通过国产化适配与云端服务，可显著降低⻛险并提升效率。技术⽆⽌境，

ail/LinkedIn/Twitter•º p> • Ž4CîïÁ%5áâŽ4CîïÁ%kð,ñ%ã•ÌòPòóñ%AIŸ ôK> • AIdeAPIõö5z÷øÕáâAPIõö,ñTU)`ùÈúæGAIdeC…‰API> • AIçèûÞ&Šü5áâ'¶ý%ã)`Šü|þÿGChatGPT!"GAIçèûÞ&> • AI*+uv5´µ#$GManusuv,!"#$%AI*+,)`%&R<º»JK> ƒD‡5†[ˆGfigma> • 2022Eb,÷‹MonicauŒ>Monica!"#¶‰$•)€GAIŸ ,$ŒÜÝÞLMŽ•áâS),•ÌQŸ%ãR²cA+C•‘W O>Monica !"#. ChatGPT API áâ()G Chrome ßà,’L !"#$%Bloomberg*&'()2 Agent()9 Agent%;<=4 !"#$%Bloomberg*&'()Agent%;<=4 ()+I±5š›x²'# AI *+Ðd³,KfJK’3)€> • *˜5LangGraphcAutogencHaystackcSwarmcMulti-agent Orchestrator> • 7⃣ de´.«Model Routing¬5š›6¦ AI de•„G()µ¶Cš·¸¤> • *˜5MartiancOpenRoutercNot Diamond> • 8⃣ ¡¹gde«Foundational Models¬5bº

在广泛的应用场景中都能发挥出色的性能。 8 / 32 LLM 基础设施：大模型框架及微调 (Fine Tuning) 大模型框架有哪些特点： ：大模型开发框架通过提供高 层次的 API 简化了复杂模型的构建过程。这 些 API 抽象掉了许多底层细节，使开发者能 够专注于模型的设计和训练策略。 ：这些框架经过优化，以充分利用 GPU、TPU 等高性能计算硬件，以加速模型 的训练和推理过程。 ：为了处理大型数据集和大规模参 Agent。在给定 AutoGPT 一个自然 语言目标后，它会尝试将其分解为多个子任务，并在自动循环中使用 互联网和其他工具来实现该目标。它使用的是 OpenAI 的 GPT-4 或 GPT-3.5 API，是首个使用 GPT-4 执行自主任务的应用程序实例。 AutoGPT 最大的特点在于能根据任务指令自主分析和执行，当收到 一个需求或任务时，它会开始分析这个问题，并且给出执行目标和具 体任务，然后开始执行。 业和开发者更高效地管理和使用这些先进的 AI 模型， 快速完成从模型到应用的跨越，如 、 等。 ： 大模型聚合平台主要用于整合和管理多个大型机器学习模型，在聚合平台之上，衍生出 MaaS（Model-as-a- Service，大模型即服务）的服务模式——通过提供统一的接口和框架，以更高效地部署、运行和优化这些模型， 。 ：其它开发相关的 LLM 工具，如云原生构建多模态AI应用的工具