0 0 1 C++

llama : quantize up to 31% faster on Linux and Windows with mmap (#3206)

* llama : enable mmap in quantize on Linux -> 31% faster

* also enable mmap on Windows

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

Cebtenzzre committed 2y ago

2777a84be429401a2b7d33c2b6a4ada1f0776f1b

Parent: 0a4a4a0

Committed by GitHub <noreply@github.com> on 9/29/2023, 1:48:45 PM