fix(llama-cpp): consistently select fallback (#3789)

* fix(llama-cpp): consistently select fallback

We didn't took in consideration the case where the host has the CPU
flagset, but the binaries were not actually present in the asset dir.

This made possible for instance for models that specified the llama-cpp
backend directly in the config to not eventually pick-up the fallback
binary in case the optimized binaries were not present.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: adjust and simplify selection

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: move failure recovery to BackendLoader()

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* comments

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* minor fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>