Fix DoS / integer overflow

[pwilkin]

Limit repetitions to 5000 max, store stoul in unsigned long.

[pwilkin]

Since it's a publicly disclosed security issue, I'm pinging a lot of people for review since it's probably best to merge this one quickly.

[pwilkin]

Fixes #17352

[ggerganov]

Think we can avoid including <optional> as it brings very little convenience while increasing the compile-time.

[pwilkin]

@ggerganov aight, changed the code to use UINT64_MAX as placeholder instead of using optional since we're not using anything above the threshold as proper values anyway.

Also after some deliberations I reduced the threshold to 2000, I don't think of any real use-cases in which a higher threshold might be needed and this will help avoid more overhead.

[ngxson]

This change potentially made one of the server test to hangs on windows: https://github.com/ggml-org/llama.cpp/actions/runs/19537370292/job/55934647432

Same behavior observed when running the test locally on a windows machine.