#include<iostream>
#include<string>
#include<cstdio>
#include<vector>
#include<cmath>
#include<algorithm>
#include<functional>
#include<iomanip>
#include<queue>
#include<ciso646>
#include<random>
#include<map>
#include<set>
#include<bitset>
#include<stack>
#include<unordered_map>
#include<utility>
#include<cassert>
#include<complex>
using namespace std;

//#define int long long
typedef long long ll;

typedef unsigned long long ul;
typedef unsigned int ui;
const ll mod = 1000000007;
const ll INF = (1e+18) + 7;
typedef pair<int, int>P;
#define stop char nyaa;cin>>nyaa;
#define rep(i,n) for(int i=0;i<n;i++)
#define per(i,n) for(int i=n-1;i>=0;i--)
#define Rep(i,sta,n) for(int i=sta;i<n;i++)
#define rep1(i,n) for(int i=1;i<=n;i++)
#define per1(i,n) for(int i=n;i>=1;i--)
#define Rep1(i,sta,n) for(int i=sta;i<=n;i++)
#define all(v) (v).begin(),(v).end()
typedef pair<ll, ll> LP;
typedef long double ld;
typedef pair<ld, ld> LDP;
const ld eps = 1e-6;
const ld pi = acos(-1.0);
//typedef vector<vector<ll>> mat;
typedef vector<int> vec;

ll mod_pow(ll a, ll n) {
	ll res = 1;
	while (n) {
		if (n & 1)res = res * a%mod;
		a = a * a%mod; n >>= 1;
	}
	return res;
}

struct modint {
	ll n;
	modint() :n(0) { ; }
	modint(ll m) :n(m) {
		if (n >= mod)n %= mod;
		else if (n < 0)n = (n%mod + mod) % mod;
	}
	operator int() { return n; }
};
bool operator==(modint a, modint b) { return a.n == b.n; }
modint operator+=(modint &a, modint b) { a.n += b.n; if (a.n >= mod)a.n -= mod; return a; }
modint operator-=(modint &a, modint b) { a.n -= b.n; if (a.n < 0)a.n += mod; return a; }
modint operator*=(modint &a, modint b) { a.n = ((ll)a.n*b.n) % mod; return a; }
modint operator+(modint a, modint b) { return a += b; }
modint operator-(modint a, modint b) { return a -= b; }
modint operator*(modint a, modint b) { return a *= b; }
modint operator^(modint a, int n) {
	if (n == 0)return modint(1);
	modint res = (a*a) ^ (n / 2);
	if (n % 2)res = res * a;
	return res;
}

//ll inv(ll a, ll p) {
//	return (a == 1 ? 1 : (1 - p * inv(p%a, a)) / a + p);
//}
//modint operator/(modint a, modint b) { return a * modint(inv(b, mod)); }

int dx[4] = { 1,0,-1,0 };
int dy[4] = { 0,1,0,-1 };

void solve() {
	int n, k; cin >> n >> k;
	ll s = (ll)n*(n + 1) / 2;
	if (s%k) {
		cout << "No" << endl; return;
	}
	if (n == k) {
		if (n == 1) {
			cout << "Yes" << endl;
			cout << "1" << endl; return;
		}
		cout << "No" << endl; return;
	}
	cout << "Yes" << endl;
	int d = n / k;
	if (d % 2 == 0) {
		int cur = 1;
		vector<vector<int>> ans(k);
		rep(i, d / 2) {
			rep(j, k) {
				ans[j].push_back(cur); cur++;
			}
			per(j, k) {
				ans[j].push_back(cur); cur++;
			}
		}
		rep(i, k) {
			rep(j, ans[i].size()) {
				if (j > 0)cout << " ";
				cout << ans[i][j];
			}
			cout << endl;
		}
		return;
	}
	else {
		int cur = 1;
		vector<vector<int>> ans(k);
		rep(i, (d - 3) / 2) {
			rep(j, k) {
				ans[j].push_back(cur); cur++;
			}
			per(j, k) {
				ans[j].push_back(cur); cur++;
			}
		}
		rep(j, k) {
			ans[j].push_back(cur); cur++;
		}
		int id = k / 2;
		rep(j, k) {
			ans[id].push_back(cur); cur++;
			id++; if (id == k)id = 0;
		}
		id = k - 1;
		rep(j, k) {
			ans[id].push_back(cur); cur++;
			id += k/2; id %= k;
		}
		rep(i, k) {
			rep(j, ans[i].size()) {
				if (j > 0)cout << " ";
				cout << ans[i][j];
			}
			cout << endl;
		}
		return;
	}
}

signed main() {
	ios::sync_with_stdio(false);
	cin.tie(0);
	cout << fixed << setprecision(5);
	//init();
	//int t; cin >> t; rep(i, t)solve();
	//while (cin >> n, n)solve();
	solve();
	stop
		return 0;
}