feat(LlamaRankingContext): add an option to chunk large documents

[giladgd]

Description of change

• feat(LlamaRankingContext): add an option to chunk large documents
• feat(LlamaModel): lazyMode support
• feat: get model and context memory usage
• feat: native jinja implementation fallback
• fix: reading gguf files that have no tensors
• fix: reading network gguf file retry conditions
• fix: add missing supported quant file name
• fix: check arch features directly from llama.cpp
• fix: align the Vulkan device reading more with llama.cpp
• fix: Metal 4 tensor API issues on M5 mac machines
• fix: various bugs

Resolves #644

Pull-Request Checklist

• Code is up-to-date with the master branch
• npm run format to apply eslint formatting
• npm run test passes with this change
• This pull request links relevant issues as Fixes #0000
• There are new or updated unit tests validating the change
• Documentation has been updated to reflect this change
• The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)

[ido-pluto]

LGTM