[menaerus]

My question wasn't about how to run multiple queries against the LLM but rather how is it even possible from transformer architecture PoV to have a single LLM hosting multiple and different end clients. I'm probably missing something but can't figure that out yet.

[lostmsu]

If you have a branchless program, you can execute the same step of the program on multiple different inputs. https://en.wikipedia.org/wiki/SIMD