Skip to content

ggml-cpu: optimise rms_norm op #16650

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+10 −15
Open

ggml-cpu: optimise rms_norm op #16650

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 6 additions & 15 deletions ggml/src/ggml-cpu/ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3534,31 +3534,22 @@ static void ggml_compute_forward_rms_norm_f32(

GGML_ASSERT(eps >= 0.0f);

// TODO: optimize
for (int64_t i03 = 0; i03 < ne03; i03++) {
for (int64_t i02 = 0; i02 < ne02; i02++) {
for (int64_t i01 = ith; i01 < ne01; i01 += nth) {
const float * x = (float *) ((char *) src0->data + i01*nb01 + i02*nb02 + i03*nb03);
float * y = (float *) ((char *) dst->data + i01*nb1 + i02*nb2 + i03*nb3);

ggml_float sum = 0.0;
for (int64_t i00 = 0; i00 < ne00; i00++) {
sum += (ggml_float)(x[i00] * x[i00]);
}

const float mean = sum/ne00;

float * y = (float *) ((char *) dst->data + i01*nb1 + i02*nb2 + i03*nb3);

memcpy(y, x, ne00 * sizeof(float));
// for (int i00 = 0; i00 < ne00; i00++) {
// y[i00] = x[i00];
// }
float sum = 0.0f;
ggml_vec_dot_f32(ne00, &sum, 0, x, 0, x, 0, 1);

const float scale = 1.0f/sqrtf(mean + eps);
const float mean = sum / ne00;
const float scale = 1.0f / sqrtf(mean + eps);

// if you hit this, likely you got an inf somewhere earlier
assert(scale > 0.0f);

ggml_vec_cpy_f32(ne00, y, x);
ggml_vec_scale_f32(ne00, y, scale);
}
}
Expand Down
4 changes: 4 additions & 0 deletions tests/test-backend-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7012,6 +7012,10 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
test_cases.emplace_back(new test_sum(GGML_TYPE_F32, it));
}

test_cases.emplace_back(new test_rms_norm(GGML_TYPE_F32, { 1024, 2, 1, 1 }, false, 1e-6f, false)); // qwen3-0.6b
test_cases.emplace_back(new test_rms_norm(GGML_TYPE_F32, { 2048, 2, 1, 1 }, false, 1e-5f, false)); // llama-3.2-1b, granite-3.3-2b
test_cases.emplace_back(new test_rms_norm(GGML_TYPE_F32, { 2880, 2, 1, 1 }, false, 1e-5f, false)); // gpt-oss-20b

return test_cases;
}

Expand Down