In-House LLM Serving at Netflix

Netflix’s AI Platform and Inference teams describe running large language models in-house, handling deployment and inference within the company’s existing production environment rather than a separate machine-learning silo. They discuss decisions and trade-offs that emerged under production load.

Image: Netflix TechBlog

Coverage 1 publisher

  1. Netflix TechBlog

    In-House LLM Serving at Netflix

Articles stay on their publishers’ sites; each link opens the original.