CYBER WATCH / EQUINOXE INTELLIGENCE
← All articles
b12232: Windows unbuffered model load (#26014)
llama.cpp Releases · 2026-11-09 22:01:39
This update fixes Windows model loading with unbuffered I/O. It corrects read‑length calculation, adds timing tests and a chunked fallback read, removes file‑pointer semantic differences between Linux and Windows, and drops unused mmap arguments. Tests are refined, duplicate constexprs removed, and label behavior added to the test suite.Read original source ↗