#include <bits/stdc++.h>
using namespace std;
typedef signed long long ll;

#undef _P
#define _P(...) (void)printf(__VA_ARGS__)
#define FOR(x,to) for(x=0;x<(to);x++)
#define FORR(x,arr) for(auto& x:arr)
#define ITR(x,c) for(__typeof(c.begin()) x=c.begin();x!=c.end();x++)
#define ALL(a) (a.begin()),(a.end())
#define ZERO(a) memset(a,0,sizeof(a))
#define MINUS(a) memset(a,0xff,sizeof(a))
//-------------------------------------------------------

ll N,K;

vector<ll> R[202020];

void solve() {
	int i,j,k,l,r,x,y; string s;
	
	cin>>N>>K;
	ll sum=N*(N+1)/2;
	if(sum%K) return _P("No\n");
	
	int P=N/K;
	
	for(i=0;i<=P;i+=2) {
		if((P-i)%K==0) {
			FOR(x,P-i) {
				FOR(y,K) {
					R[(x+y)%K].push_back(x*K+y+1);
				}
			}
			FOR(x,i) {
				FOR(y,K) {
					if(x%2==0) R[y].push_back((x+(P-i))*K+y+1);
					else R[K-1-y].push_back((x+(P-i))*K+y+1);
				}
			}
			cout<<"Yes"<<endl;
			FOR(i,K) {
				FORR(c,R[i]) cout<<c<<" ";
				cout<<endl;
			}
			return;
		}
	}
	assert(0);
	cout<<"No"<<endl;
}


int main(int argc,char** argv){
	string s;int i;
	if(argc==1) ios::sync_with_stdio(false), cin.tie(0);
	FOR(i,argc-1) s+=argv[i+1],s+='\n'; FOR(i,s.size()) ungetc(s[s.size()-1-i],stdin);
	cout.tie(0); solve(); return 0;
}