#include <iostream>
#include <algorithm>
#include <iomanip>
#include <vector>
#include <queue>
#include <deque>
#include <set>
#include <map>
#include <tuple>
#include <cmath>
#include <numeric>
#include <functional>
#include <cassert>

#define debug_value(x) cerr << "line" << __LINE__ << ":<" << __func__ << ">:" << #x << "=" << x << endl;
#define debug(x) cerr << "line" << __LINE__ << ":<" << __func__ << ">:" << x << endl;

template<class T> inline bool chmax(T& a, T b) { if (a < b) { a = b; return 1; } return 0; }
template<class T> inline bool chmin(T& a, T b) { if (a > b) { a = b; return 1; } return 0; }

using namespace std;
typedef long long ll;

template<typename T>
vector<vector<T>> vec2d(int n, int m, T v){
    return vector<vector<T>>(n, vector<T>(m, v));
}

template<typename T>
vector<vector<vector<T>>> vec3d(int n, int m, int k, T v){
    return vector<vector<vector<T>>>(n, vector<vector<T>>(m, vector<T>(k, v)));
}

template<typename T>
void print_vector(vector<T> v, char delimiter=' '){
    if(v.empty()) {
        cout << endl;
        return;
    }
    for(int i = 0; i+1 < v.size(); i++) cout << v[i] << delimiter;
    cout << v.back() << endl;
}

vector<vector<int>> solve(ll n, ll k){
    ll l = n/k;
    vector<vector<int>> ans(k);
    if(l%2 == 0){
        for(int i = 0; i < l; i++){
            for(int j = 0; j < k; j++){
                ll x = i*k+j;
                if(i%2 == 0){
                    ans[j].push_back(x+1);
                }else{
                    ans[k-1-j].push_back(x+1);
                }
            }
        }
        return ans;
    }
    if(l < k){
        return {};
    }
    for(int i = 0; i < k; i++){
        for(int j = 0; j < k; j++){
            ll x = i*k+j;
            ans[(i+j)%k].push_back(x+1);
        }
    }
    if(k != l){
        auto ans1 = solve(n-k*k, k);
        for(int i = 0; i < k; i++){
            for(int x: ans1[i]) ans[i].push_back(x+k*k);
        }
    }
    return ans;
}

int main(){
    ios::sync_with_stdio(false);
    cin.tie(0);
    cout << setprecision(10) << fixed;
    ll n, k; cin >> n >> k;
    ll m = (n*(n+1))/2;
    if(m%k != 0){
        cout << "No" << endl;
        return 0;
    }
    auto ans = solve(n, k);
    if(ans.empty()){
        cout << "No" << endl;
        return 0;
    }
    cout << "Yes" << endl;
    for(int j = 0; j < k; j++){
        print_vector(ans[j]);
    }
        
}