for (int i = 0; i < np; i += GGML_F32_STEP) {
for (int j = 0; j < GGML_F32_ARR; j++) {
ay[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
- ay[j] = GGML_F32_VEC_FMA(ay[j], vs, vb);
+ ay[j] = GGML_F32_VEC_FMA(vb, ay[j], vs);
GGML_F32_VEC_STORE(y + i + j*GGML_F32_EPR, ay[j]);
}
test_cases.emplace_back(new test_add1());
test_cases.emplace_back(new test_scale());
test_cases.emplace_back(new test_scale(GGML_TYPE_F32, {10, 10, 10, 10}, 2.0f, 1.0f));
+ test_cases.emplace_back(new test_scale(GGML_TYPE_F32, {100, 10, 10, 10}, 2.0f, 1.0f));
test_cases.emplace_back(new test_softcap(GGML_TYPE_F32, {10, 10, 10, 10}, 50.0f));
test_cases.emplace_back(new test_silu_back());