西门子 -基于llm-d和Kubernetes的分布式推理 Distributed Inference with llm-d and Kubernetes.docx

西门子 -基于llm-d和Kubernetes的分布式推理 Distributed Inference with llm-d and Kubernetes.docx

DistributedInferencewithllm-dandKubernetes

AntonioCardace

PrincipalMachineLearningEngineerInferenceEngineering

RedHat

Agenda

Overviewoftheproject

Whatisllm-d

Whyllm-d

Whatchallengesdoesllm-dsolvePhasesofInference

Architectureoverview

Well-litpaths

Demo

您可能关注的文档

文档评论(0)

1亿VIP精品文档

相关文档