llama : add `use_direct_io` flag for model loading (#18166)

llama : add `use_direct_io` flag for model loading (#18166)

* Adding --direct-io flag for model loading

* Fixing read_raw() calls

* Fixing Windows read_raw_at

* Changing type off_t to size_t for windows and Renaming functions

* disable direct io when mmap is explicitly enabled

* Use read_raw_unsafe when upload_backend is available, not functional on some devices with Vulkan and SYCL

* Fallback to std::fread in case O_DIRECT fails due to bad address

* Windows: remove const keywords and unused functions

* Update src/llama-mmap.cpp

Co-authored-by: Georgi Gerganov <redacted>
---------

Co-authored-by: jtischbein <redacted>
Co-authored-by: Georgi Gerganov <redacted>