更智能地扩展：深入了解 Databricks 如何优化模型服务.pdf

1、Forward-looking StatementThis presentation has been prepared for informational purposes only.The information set forth herein does not purport to be complete or contain all relevant information.Statements contained herein are made as of the date of this presentation unless stated otherwise.This pres

2、entation and the accompanying oral commentary may contain forward-looking statements.In some cases,forward-looking statements can be identified by terms such as“may”,“will”,“should”,“expects”,“plans”,“anticipates”,“could”,“intends”,“projects”,“believes”,“estimates”,“predicts”,or“continue”,or the neg

3、ative of these words or other similar terms or expressions that concern Databricks expectations,strategy,plans,or intentions.Forward-looking statements are based on information available at the time those statements are made and are inherently subject to risks and uncertainties that could cause actu

4、al results to differ materially from those expressed in or suggested by the forward-looking statements.Forward-looking statements should not be read as a guarantee of future performance or outcomes.Except as required by law,Databricks does not undertake any obligation to publicly update or revise an

5、y forward-looking statement,whether as a result of new information,future developments or otherwise.3Scaling Smarter:Optimizing FoundationModel ServingAsfandyar QureshiJune/12/2025Mosaic AI Model ServingFoundationDatabricks-hosted GenAI models,such as Meta Llama 4Hosted on cutting-edge GPUs and opti

6、mized inference runtimesCustomMLflow models(XGBoost,PyTorch,Hugging Face transformers,etc)AI agent endpointsServed on CPU or a variety of GPU typesProprietarySecure access to proprietary models,such as Anthropic Claude5Unified deployment and governance for AI models and agentsRapid growth in usageEm