Refactor llama-model.cpp

[pwilkin]

@ggerganov I know you said you were planning to do it, but honestly it's been a nightmare working on all the model implementations with the huge llama-model.cpp, so I wanted to just get the "easy" albeit tedious part out of the way. Moved all llm_build_* definitions to their separate class files in src/models/

[CISC]

This is a nightmare to review and rebase until merged though, also you seem to have pushed the same changes to your Qwen3-Next PR?

[pwilkin]

@CISC Ye, need them for working there, but I'll revert once I'm done (unless this is done first and I can merge on top).

I know it's a nightmare, I already kind of went through it when I asked an LLM to automate some tasks and it proceeded merrily ripping out methods just because some classes didn't inherit from llm_graph_context :>

If you want, I can write a script that runs tree-sitter on the original definitions in llama-model.cpp vs the new classes and shows any differences to verify that nothing was accidentally lost.

[jacekpoplawski]

Maybe it would be easier to refactor that partially, just a subset of the models?

[ngxson]

This seems to be a good change, just have some other ideas:

1. I think for now all models can share one single .h file. The main .cpp implementation can be split into smaller files as proposed here
2. Our naming convention uses - instead of _. Maybe just src/models/(model-name).cpp is enough, no need the llm_build prefix. For example: src/models/gpt2.cpp