llama.cpp [just adopted it](https://github.com/ggerganov/llama.cpp/pull/10570), and that's also what [gemma.cpp](https://github.com/google/gemma.cpp) uses. Some options: - [x] Retire nonstd_make_unique backfill - [x] Destructure pairs - [ ] std::optional for attempted parsing - [ ] std::variant for Value? - [ ] More elegant function / filter definitions (leverage new auto inference) - [ ] (in the process, optionally make the dep to json a bit looser to be able to switch to [json.cpp](https://github.com/jart/json.cpp))
llama.cpp just adopted it, and that's also what gemma.cpp uses.
Some options: