Viewing profile — bytepoet

Thanks for tiny-vllm! The documentation is amazing. I'm using it as a resource for a university course I'm teaching.

Wonderful! Great, detailed explanation. I look forward to reading the vLLM post as well.

Thanks for the inputs. It's very helpful to know. I look forward to following mirage development.

This is very cool. I enjoyed going through the writeup and GitHub README. I was wondering if these same optimizations can be brought to bear on training as well, rather than only i…

I really enjoyed reading this, particularly the first part where the author was specific about why we invariably (and often vaguely) find LLM generated text slightly off. I cherish…

I enjoyed reading this paper. The experiments are well-designed and it's well-written. Much work on generalization of ML models deals with asymptotic bounds. Here, there's a precis…

Such a well-written and thoughtful blog post. Loved it!

The inability of LLMs of ask for clarification was exactly the flaw we encountered when testing them on open-ended problems, stated somewhat ambiguously. This was in the context of…

The blog post is really good. I see that there's a follow-up piece 'The Fifth Kind of Optimisation' about parallelism. Something that I'd like to add is that it's helpful to unders…

Thanks a lot, Sasha, for creating these. I found your LLM training puzzles to be excellent as well.