DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: support packed INT4 convrot models (#2276)

Browse Source 
Co-authored-by: noctrex <noctrex@gmail.com>
This commit is contained in:
leejetandnoctrex authored and GitHub committed 2026-11-06 00:35:58 +08:00
1 parent 58bb3c1b1c
commit 7952693004
48 files changed
+2003 -102
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/diffusion_engine.cpp
+2 -2
View File
@@ -1019,7 +1019,7 @@ void StableDiffusionGGML::configure_weight_loading() {
bool have_int8_tensorwise = false;
bool have_quant_type_rule = false;
for (const auto& [_, tensor_storage] : model_loader.get_tensor_storage_map()) {
if (tensor_storage.is_int8_tensorwise) {
if (tensor_storage.is_int8_tensorwise || tensor_storage.w4_convrot_kind) {
have_int8_tensorwise = true;
}
if (tensor_storage.expected_type < GGML_TYPE_COUNT && ggml_is_quantized(tensor_storage.expected_type)) {
@@ -1051,7 +1051,7 @@ void StableDiffusionGGML::configure_weight_loading() {
} else if (sd_ctx_params->lora_apply_mode == LORA_APPLY_IMMEDIATELY) {
if (have_int8_tensorwise) {
LOG_WARN(
"INT8 tensorwise weights do not support the immediately LoRA apply mode; "
"ComfyUI INT8/packed INT4 weights do not support the immediately LoRA apply mode; "
"using at_runtime instead");
apply_lora_immediately = false;
} else if (row_split_active()) {