ML Inference (SGLang) for Engineers: A Primer
Hosted by Joel
Registration
Past Event
About Event
We will go through an introduction of
Mini-SGLang https://github.com/sgl-project/mini-sglang which is a minified version of SGLang, which is a high-performance serving framework for large language models.
We assume knowledge of programming and data structures at the undegraduate level. Knowledge of Transformers is helpful but not required - we will add explainers as needed.
Talk will be streamed to YouTube.
Location
Network School Library