upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-09-25 07:27:53 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: enable single-GPU auto-fit with tiered parameter placement (#1942)

Browse Source
This commit is contained in:
leejet
2026-09-07 00:18:42 +08:00
committed by GitHub
parent dbb611264e
commit 80bac2d5fc
5 changed files with 408 additions and 330 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/common/common.cpp
+23 -6
View File
@@ -548,12 +548,6 @@ ArgOptions SDContextParams::get_options() {
"--eager-load",
"load all params into the params backend at model-load time instead of lazily on first use (defaults to false)",
true, &eager_load},
{"",
"--auto-fit",
"pick the diffusion/te/vae device placements automatically from the model size and the per-device "
"memory budgets (--max-vram; defaults to free memory minus a small margin). Overrides --backend and "
"--params-backend; may split modules across GPUs (--split-mode still selects layer or row)",
true, &auto_fit},
{"",
"--force-sdxl-vae-conv-scale",
"force use of conv scale on sdxl vae",
@@ -596,6 +590,23 @@ ArgOptions SDContextParams::get_options() {
true, &vae_conv_direct},
};
auto on_auto_fit_arg = [&](int argc, const char** argv, int index) {
if (++index >= argc) {
LOG_ERROR("--auto-fit requires 'on' or 'off'");
return -1;
}
const std::string arg = argv[index];
if (arg == "on") {
auto_fit = true;
} else if (arg == "off") {
auto_fit = false;
} else {
LOG_ERROR("invalid --auto-fit value '%s'; expected 'on' or 'off'", argv[index]);
return -1;
}
return 1;
};
auto on_type_arg = [&](int argc, const char** argv, int index) {
if (++index >= argc) {
return -1;
@@ -667,6 +678,12 @@ ArgOptions SDContextParams::get_options() {
};
options.manual_options = {
{"",
"--auto-fit",
"on|off (default: on). Use one GPU for diffusion/te/vae computation and place weights on that GPU, "
"RAM, another GPU, or disk in that order, according to available memory (--max-vram limits GPU budgets). "
"Disabled by explicit --backend or --params-backend; uses automatic graph segmentation when needed",
on_auto_fit_arg},
{"",
"--type",
"weight type (examples: f32, f16, q4_0, q4_1, q5_0, q5_1, q8_0, q2_K, q3_K, q4_K). "