upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-09-28 17:08:05 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix: map mmapped weights through Metal buffers instead of CPU buffers (#2037)

Browse Source
This commit is contained in:
Dong Wang
2026-09-24 00:53:49 +08:00
committed by GitHub
parent 2a4ebba818
commit 500ef5fa7c
6 changed files with 139 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/backend.md
+3
View File
@@ -161,6 +161,9 @@ resident allocations. Vulkan reports exceeding total memory are rejected because
its heap-budget subtraction can underflow. Other backends use the cap instead of
treating such reports as zero free memory. Failed checks log the reported free and
total memory alongside tracked weight and runtime allocations.
With `--mmap`, device-backed mappings count toward these budgets at their full
mapped-file size, once per device buffer even when multiple parameter blocks
share it. Mappings retained in the loader cache continue to count.
Components are considered in `diffusion`, `te`, `vae` order so that repeatedly
used diffusion weights have priority. Each component's weights use the first