Calculate Scaled Dot-Product Attention
* Queries Q (shape N × D)
* Keys K (shape N × D)
* Values V (shape N × D)
// 1) Q * K / sqrt(d_k)
vector<vector<float>> scores(N, vector<float>(N, 0));
const float inv_sqrt_d = 1.f / sqrt(D);
for (long long i = 0; i < N; ++i)
for (long long j = 0; j < N; ++j) {
float sum = 0;
for (int k = 0; k < D; ++k) sum += Q[i][k] * K[j][k];
scores[i][j] = sum * inv_sqrt_d;
}
// 2) Row‑wise softmax
vector<vector<float>> attn(N, vector<float>(N, 0));
for (long long i = 0; i < N; ++i) {
float maxv = *max_element(scores[i].begin(), scores[i].end());
vector<float> expv(N);
for (long long j = 0; j < N; ++j)
expv[j] = exp(scores[i][j] - maxv);
float sum = 0;
for (long long j = 0; j < N; ++j) sum += expv[j];
for (long long j = 0; j < N; ++j) attn[i][j] = expv[j] / sum;
}
// 3) attn · V
vector<vector<float>> out(N, vector<float>(D, 0));
for (long long i = 0; i < N; ++i)
for (long long j = 0; j < N; ++j)
for (int k = 0; k < D; ++k)
out[i][k] += attn[i][j] * V[j][k];
reduction(+:sum) are availableI don’t have enough time, so this problem is straightforward. I want to try entire LLM inference.