Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA

6 comments

• yu3zhou4 1 hour ago
  README is in my opinion (author here) the most interesting - I wrote it to help others build useful mental model to be able to recreate the project yourself, without need to even read my code
• dwa3592 9 minutes ago
  Very nice job on read me.

  >>Physically, LLM is a file which contains a lot of float numbers.

  aka atoms of the LLM.

  [-]
  • cyanydeez 4 minutes ago
    the universe is just atomic if statments
• juancn 38 minutes ago
  Looks interesting, it reminds me of the first llama.cpp, but better documented.
• einpoklum 7 minutes ago
  It seems the author believes checking the return values of CUDA API calls is not "tiny" enough :-(
• nazgulsenpai 1 hour ago
  I love the documentation formatted in lessons. I can't wait to read through it.
• harshuljain13 9 minutes ago
  [dead]