#include <bits/stdc++.h>

#include <unistd.h>
 
using namespace std;
 
#define DEBUG(x) cerr<<#x<<": "<<x<<endl;
#define DEBUG_VEC(v) cerr<<#v<<":";for(int i=0;i<v.size();i++) cerr<<" "<<v[i]; cerr<<endl
#define DEBUG_MAT(v) cerr<<#v<<endl;for(int i=0;i<v.size();i++){for(int j=0;j<v[i].size();j++) {cerr<<v[i][j]<<" ";}cerr<<endl;}
 
 
typedef long long ll;
#define int ll
 
#define vi vector<int>
#define vl vector<ll>
#define vii vector< vector<int> >
#define vll vector< vector<ll> >
#define vs vector<string>
#define pii pair<int,int>
#define pis pair<int,string>
#define psi pair<string,int>
#define pll pair<ll,ll>
template<class S, class T> pair<S, T> operator+(const pair<S, T> &s, const pair<S, T> &t) { return pair<S, T>(s.first + t.first, s.second + t.second); }
template<class S, class T> pair<S, T> operator-(const pair<S, T> &s, const pair<S, T> &t) { return pair<S, T>(s.first - t.first, s.second - t.second); }
template<class S, class T> ostream& operator<<(ostream& os, pair<S, T> p) { os << "(" << p.first << ", " << p.second << ")"; return os; }
#define X first
#define Y second
#define rep(i,n) for(int i=0;i<(n);i++)
#define rep1(i,n) for(int i=1;i<=(n);i++)
#define rrep(i,n) for(int i=(n)-1;i>=0;i--)
#define rrep1(i,n) for(int i=(n);i>0;i--)
#define REP(i,a,b) for(int i=a;i<b;i++)
#define in(x, a, b) (a <= x && x < b)
#define all(c) c.begin(),c.end()
template<class T> bool chmax(T &a, const T &b) { if (a<b) { a = b; return 1; } return 0; }
template<class T> bool chmin(T &a, const T &b) { if (a>b) { a = b; return 1; } return 0; }
#define UNIQUE(v) v.erase(std::unique(v.begin(), v.end()), v.end());
const ll inf = 1000000001;
const ll INF = (ll)1e18 + 1;
const double pi = 3.14159265358979323846;
#define Sp(p) cout<<setprecision(15)<< fixed<<p<<endl;
int dx_ori[4] = { -1,0, 1,0 }, dy_ori[4] = { 0,1,0,-1 };
int dx[4] = {0, 0, 0, 0}, dy[4] = {0, 0, 0, 0};
int dx2[8] = { 1,1,0,-1,-1,-1,0,1 }, dy2[8] = { 0,1,1,1,0,-1,-1,-1 };
#define fio() cin.tie(0); ios::sync_with_stdio(false);
const ll MOD = 1000000007;
//const ll MOD = 998244353;
// #define mp make_pair
//#define endl '\n'

void solve1(int n, int k) {
  int m = n / k;
  vii a(k);
  int nex = 1;
  rep (_, m / 2) {
    rep (i, k) {
      a[i].push_back(nex);
      nex++;
    }
    rrep (i, k) {
      a[i].push_back(nex);
      nex++;
    }
  }
  cout << "Yes" << endl;
  rep (i, k) {
    rep (j, m) {
      cout << a[i][j] << " ";
    }
    cout << endl;
  }
}

void solve2(int n, int k) {
  int m = n / k;
  if (m == 1) {
    if (n == 1) {
      cout << "Yes" << endl;
      cout << 1 << endl;
    }
    else {
      cout << "No" << endl;
    }
    return;
  }
  
  cout << "Yes" << endl;
  int nex = n;
  vii a(k);
  while (m > 3) {
    rep (i, k) {
      a[i].push_back(nex--);
      n--;
    }
    rrep (i, k) {
      a[i].push_back(nex--);
      n--;
    }
    m -= 2;
  }

  int one = n * (n + 1) / 2 / k;
  rep (i, k) {
    a[i].push_back(i + 1);
  }
  int idx = one - (2 * k + 2*k + 1);
  int i = idx - 1;
  rep (_, k) {
    a[i].push_back(2*k + 1 + _);
    i++;
    i %= k;
  }
  rep (i, k) {
    a[i].push_back(one - a[i][a[i].size() - 1] - a[i][a[i].size() - 2]);
  }

  rep (i, k) {
    rep (j, a[i].size()) {
      cout << a[i][j] << " ";
    }
    cout << endl;
  }
}

signed main() {
  ll n, k;
  cin >> n >> k;
  if (n % k != 0) {
    cout << "No" << endl;
    return 0;
  }
  if ((n * (n + 1) / 2) % k != 0) {
    cout << "No" << endl;
    return 0;
  }

  if ((n / k) % 2 == 0) {
    solve1(n, k);
  }
  else {
    solve2(n, k);
  }
}