#include <bits/stdc++.h>
#define rep(i, a) for (int i = (int)0; i < (int)a; ++i)
#define rrep(i, a) for (int i = (int)a - 1; i >= 0; --i)
#define REP(i, a, b) for (int i = (int)a; i < (int)b; ++i)
#define RREP(i, a, b) for (int i = (int)a - 1; i >= b; --i)
#define pb push_back
#define eb emplace_back
#define all(x) x.begin(), x.end()
#define rall(x) x.rbegin(), x.rend()
#define popcount __builtin_popcount
using ll = long long;
constexpr ll mod = 1e9 + 7;
constexpr ll INF = 1LL << 60;

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

ll gcd(ll n, ll m)
{
	ll tmp;
	while (m != 0)
	{
		tmp = n % m;
		n = m;
		m = tmp;
	}
	return n;
}

ll lcm(ll n, ll m)
{
	return abs(n) / gcd(n, m) * abs(m); //gl=xy
}

using namespace std;

void solve()
{
	ll n,k;
	cin>>n>>k;
	ll sum=(n+1)*n/2;
	if(sum%k==0){
		cout<<"Yes\n";
		vector<vector<ll>>v(n/k);
		rep(i,n){
			v[i/k].pb(i+1);
		}
		rep(i,k){
			int m=i;
			rep(j,n/k/2){
				if(j)cout<<" ";
				cout<<v[j][m]<<" ";
				cout<<v[n/k-1-j][k-1-m];
			}
			cout<<"\n";
		}
	}
	else cout<<"No\n";
}

int main()
{
	ios::sync_with_stdio(false);
	cin.tie(0);
	cout << fixed << setprecision(15);
	solve();
	return 0;
}