llama.cpp
quantize: cap working memory size to avoid loading big tensors onto RAM
#27795
Merged
Merged
quantize: cap working memory size to avoid loading big tensors onto RAM #27795
ngxson
merged
1 commit into
master
from
xsn/quant_cap
quantize: cap working memory size to avoid loading big tensors onto RAM
c0c7fa93
ServeurpersoCom
approved these changes
on 2026-08-27
Reviewers
Assignees
No one assigned
Labels
examples
Milestone
No milestone
Login to write a write a comment.
Login via GitHub