DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-14 04:47:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: guard GPU memory capacity and propagate encoding failures

Browse Source
This commit is contained in:
leejet committed 2026-09-11 01:05:30 +08:00
1 parent 14eddb32b1
commit 58d3f6e240
5 files changed
+72 -22
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/backend.md
+5
View File
@@ -149,6 +149,11 @@ GiB", and with no budget set each device's free memory minus a 512 MiB margin
is used. These resolved GPU budgets, including the safety margin, also drive
the runner's graph-cut capacity checks.
Runtime capacity checks also leave 512 MiB of currently free device memory for
backend scratch buffers and pipelines, including with explicit backend assignments.
They cap stale free-memory reports by the device's total memory minus tracked
resident allocations and reject reports that exceed the device's total memory.
Components are considered in `diffusion`, `te`, `vae` order so that repeatedly
used diffusion weights have priority. Each component's weights use the first
storage location with enough remaining budget: