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

fix: keep scaled INT8 convrot matmuls on Vulkan (#2070)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-09-27 20:43:06 +08:00
1 parent 27f7c430c0
commit 42ab1c12f1
2 files changed
+10 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/core/ggml_extend.cpp
+8 -2
View File
@@ -255,14 +255,20 @@ ggml_tensor* ggml_ext_linear_i8_tensorwise(ggml_context* ctx,
}
ggml_tensor* fused_bias = scale == 1.f ? b : nullptr;
auto mul_mat = [&](ggml_tensor* input) {
if (input->type == GGML_TYPE_F32 && convrot_group_size > 0) {
input = ggml_quantize_i8_convrot(ctx, input, convrot_group_size);
}
return ggml_mul_mat_i8_tensorwise(ctx, w, input, weight_scale, fused_bias, convrot_group_size);
};
if (x->ne[2] * x->ne[3] > 1024) {
int64_t ne2 = x->ne[2];
int64_t ne3 = x->ne[3];
x = ggml_reshape_2d(ctx, x, x->ne[0], x->ne[1] * x->ne[2] * x->ne[3]);
x = ggml_mul_mat_i8_tensorwise(ctx, w, x, weight_scale, fused_bias, convrot_group_size);
x = mul_mat(x);
x = ggml_reshape_4d(ctx, x, x->ne[0], x->ne[1] / ne2 / ne3, ne2, ne3);
} else {
x = ggml_mul_mat_i8_tensorwise(ctx, w, x, weight_scale, fused_bias, convrot_group_size);
x = mul_mat(x);
}
if (scale != 1.f) {