#define _USE_MATH_DEFINES
#include <bits/stdc++.h>
using namespace std;

//template
#define rep(i,a,b) for(int i=(a);i<(b);i++)
#define rrep(i,a,b) for(int i=(a);i>(b);i--)
#define ALL(v) (v).begin(),(v).end()
typedef long long int ll; const int inf = 0x3fffffff; const ll INF = 0x3fffffffffffffff;
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; }
//template end

vector<int> ans[200010];

int main(){
    int n,k; scanf("%d%d",&n,&k);
    int m=n/k;
    if(n==1){
        printf("Yes\n"); puts("1");
        return 0;
    }
    if(((n%2==0)&&m&1)||m==1){printf("No\n"); return 0;}
    printf("Yes\n");
    if(m%2==0){
        int cnt=1;
        rep(i,0,k){
            rep(j,0,m/2){
                ans[i].push_back(cnt); ans[i].push_back(n+1-cnt);
                cnt++;
            }
        }
    }
    else{
        rep(i,0,k)ans[i].resize(3);
        rep(i,0,k)ans[i][0]=i+1;
        int idx=k-1,val=k+1;
        while(idx>=0){
            ans[idx][1]=val; ans[k-1-idx][2]=4*k+1-val;
            idx-=2; val++;
        } idx=k-2;
        while(idx>=0){
            ans[idx][1]=val; ans[k-1-idx][2]=4*k+1-val;
            idx-=2; val++;
        }val=1;
        rep(i,0,k)rep(rot,0,(m-3)/2){
            ans[i].push_back(val+3*k); ans[i].push_back(n+1-val);
            val++;
        }
    }
    rep(i,0,k){
        rep(j,0,m)printf("%d ",ans[i][j]);
        puts("");
    }
    return 0;
}