在 Oracle 云上使用 AMD Instinct GPU 大规模提供内存密集型 LLM 服务 [LRN1371]（2）.pdf

1、 LLM Inference on OCI with AMD InstinctGPUDeploy LLM using AMD MI300X on OCIGautam KarmakarMaster Principal Solution ArchitectNA Cloud Engineering,Oracle Cloud InfrastructureOctober 14,2025 LLM Inference on OCI with AMD Instinct GPUsDeploy LLM using AMD MI300X on OCIBinh ChuSr.Product ManagerDatacen

2、ter GPUsOctober 14,2025The following is intended to outline our general product direction.It is intended for information purposes only,and may not be incorporated into any contract.It is not a commitment to deliver any material,code,or functionality,and should not be relied upon in making purchasing

3、 decisions.The development,release,timing,and pricing of any features or functionality described for Oracles products may change and remains at the sole discretion of Oracle Corporation.Safe harbor statement3Copyright 2025,Oracle and/or its affiliates|Confidential:Internal/Restricted/Highly Restrict

4、edForward-Looking statementsThis presentation is intended to outline our general product direction.It is intended for information purposes only,and may not be incorporated into any contract.It is not a commitment to deliver any material,code,or functionality,and should not be relied upon in making p

5、urchasing decisions.The development,release,timing,and pricing of any features or functionality described for Oracles products may change and remains at the sole discretion of Oracle Corporation.Statements in this presentation relating to Oracles future plans,expectations,beliefs,intentions,and pros

6、pects are“forward-looking statements”and are subject to material risks and uncertainties.A detailed discussion of these factors and other risks that affect our business is contained in Oracles Securities and Exchange Commission(SEC)filings,including our most recent reports on Form 10-K and Form 10-Q