Skip to content

LLM inference in C/C++

C++ ggml

ggml-cpu : fix soft_max_back wrong output when dst aliases src1 (#27096)

Yash Raj Pandeydd4c286f3809
diff --git a/ggml/src/ggml-cpu/ops.cpp b/ggml/src/ggml-cpu/ops.cpp
index 3e377298f3..16a916d20a 100644
--- a/ggml/src/ggml-cpu/ops.cpp
+++ b/ggml/src/ggml-cpu/ops.cpp
@@ -6012,11 +6012,10 @@ static void ggml_compute_forward_soft_max_ext_back_f32(
// linear runtime, no additional memory
float dot_y_dy = 0;
- ggml_vec_dot_f32 (nc, &dot_y_dy, 0, y, 0, dy, 0, 1);
- ggml_vec_cpy_f32 (nc, dx, dy);
- ggml_vec_acc1_f32 (nc, dx, -dot_y_dy);
- ggml_vec_mul_f32 (nc, dx, dx, y);
- ggml_vec_scale_f32(nc, dx, scale);
+ ggml_vec_dot_f32(nc, &dot_y_dy, 0, y, 0, dy, 0, 1);
+ for (int i = 0; i < nc; i++) {
+ dx[i] = scale * (dy[i] - dot_y_dy) * y[i];
+ }
#ifndef NDEBUG
for (int i = 0; i < nc; ++i) {