This talk covers Grammarly's approach to using a combination of third-party LLM APIs and in-house LLMs, the role of LLMs in Grammarly's product offerings, an overview of the tools and processes used in our ML infrastructure, and how we address challenges such as access, cost control, and load testing of LLMs, sharing our experience in optimizing and serving LLMs.
talk-data.com
C
Speaker
Christoph Stuber
1
talks
Software Engineer
Grammarly
Grammarly software engineer focused on ML infrastructure and serving LLMs; uses a combination of third-party LLM APIs and in-house LLMs.
Bio from: Mastering LLM Serving and Management at Grammarly
Filter by Event / Source
Talks & appearances
1 activities · Newest first