DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: auto-detect max VRAM budget with --max-vram -1 (#1498)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-05-16 16:14:25 +08:00
1 parent fd1a2794f3
commit 38b14adb67
7 files changed
+65 -10
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/cli/README.md
+1 -1
View File
@@ -55,7 +55,7 @@ Context Options:
then threads will be set to the number of CPU physical cores
--chroma-t5-mask-pad <int> t5 mask pad size of chroma
--max-vram <float> maximum VRAM budget in GiB for graph-cut segmented execution. 0 disables
graph splitting
graph splitting; -1 auto-detects free VRAM minus 1 GiB
--force-sdxl-vae-conv-scale force use of conv scale on sdxl vae
--offload-to-cpu place the weights in RAM to save VRAM, and automatically load them into VRAM
when needed
examples/common/common.cpp
+1 -1
View File
@@ -397,7 +397,7 @@ ArgOptions SDContextParams::get_options() {
options.float_options = {
{"",
"--max-vram",
"maximum VRAM budget in GiB for graph-cut segmented execution. 0 disables graph splitting",
"maximum VRAM budget in GiB for graph-cut segmented execution. 0 disables graph splitting; -1 auto-detects free VRAM minus 1 GiB",
&max_vram},
};
examples/server/README.md
+1 -1
View File
@@ -157,7 +157,7 @@ Context Options:
then threads will be set to the number of CPU physical cores
--chroma-t5-mask-pad <int> t5 mask pad size of chroma
--max-vram <float> maximum VRAM budget in GiB for graph-cut segmented execution. 0 disables
graph splitting
graph splitting; -1 auto-detects free VRAM minus 1 GiB
--force-sdxl-vae-conv-scale force use of conv scale on sdxl vae
--offload-to-cpu place the weights in RAM to save VRAM, and automatically load them into VRAM
when needed