Inside vLLM: The Engine Powering Open-Source AI

The fun thought experiment is if GPUs dropped in price by 99%, then do we get back to a real open source world?. If moderation is never solved, in the future, people will go to open way by default.

It goes beyond the title with direct discussion of like, model, open, including: If moderation is never solved, in the future, people will go to open way by default.

1. 01VLOM is an inference engine
2. 02Their newest chip will make sure VLAM can run on them
3. 03And in a lot of cases, they use VLAM as a benchmark