#include <bits/stdc++.h>

using namespace std;

using ll = long long;

bool judge(ll n, ll K, vector< vector<ll> >& ans) {
    ll sum = n * (n + 1) / 2;
    ll mini_sum = sum / K;
    for (vector<ll>& v : ans) {
        ll tmp = 0;
        for (ll x : v) tmp += x;
        if (mini_sum != tmp) return false;
    }
    return true;
}

int main() {
    cin.tie(nullptr);
    ios::sync_with_stdio(false);
    ll n, K;
    cin >> n >> K;
    ll sum = n * (n + 1) / 2;
    if (sum % K != 0) {
        cout << "No\n";
        return 0;
    }

    vector< vector<ll> > ans(K);
    for (int i = 0; i < n / K; i++) {
        for (int j = 0; j < K; ++j) {
            ans[j].push_back(i * K + (i + j) % K + 1);
        }
    }

    if (!judge(n, K, ans)) {
        cout << "No\n";
        return 0;
    }

    cout << "Yes\n";
    for (int i = 0; i < ans.size(); i++) {
        for (int j = 0; j < ans[i].size(); ++j) {
            cout << ans[i][j] << " \n"[j + 1 == ans[i].size()];
        }
    }
    return 0;
}