#include <bits/stdc++.h>
#define whlie while
#define pb push_back
#define eb emplace_back
#define fi first
#define se second
#define rep(i,N) for(int i = 0; i < (N); i++)
#define repr(i,N) for(int i = (N) - 1; i >= 0; i--)
#define rep1(i,N) for(int i = 1; i <= (N) ; i++)
#define repr1(i,N) for(int i = (N) ; i > 0 ; i--)
#define each(x,v) for(auto& x : v)
#define all(v) (v).begin(),(v).end()
#define sz(v) ((int)(v).size())
#define ini(...) int __VA_ARGS__; in(__VA_ARGS__)
#define inl(...) ll __VA_ARGS__; in(__VA_ARGS__)
#define ins(...) string __VA_ARGS__; in(__VA_ARGS__)
using namespace std; void solve();
using ll = long long; using vl = vector<ll>;
using vi = vector<int>; using vvi = vector< vector<int> >;
constexpr int inf = 1001001001;
constexpr ll infLL = (1LL << 61) - 1;
struct IoSetupNya {IoSetupNya() { cin.tie(nullptr); ios::sync_with_stdio(false); cout << fixed << setprecision(15); cerr << fixed << setprecision(7);} } iosetupnya;
template<typename T, typename U> inline bool amin(T &x, U y) { return (y < x) ? (x = y, true) : false; }
template<typename T, typename U> inline bool amax(T &x, U y) { return (x < y) ? (x = y, true) : false; }
template<typename T, typename U> ostream& operator <<(ostream& os, const pair<T, U> &p) { os << p.first << " " << p.second; return os; }
template<typename T, typename U> istream& operator >>(istream& is, pair<T, U> &p) { is >> p.first >> p.second; return is; }
template<typename T> ostream& operator <<(ostream& os, const vector<T> &v) { int s = (int)v.size(); rep(i,s) os << (i ? " " : "") << v[i]; return os; }
template<typename T> istream& operator >>(istream& is, vector<T> &v) { for(auto &x : v) is >> x; return is; }
void in(){} template <typename T,class... U> void in(T &t,U &...u){ cin >> t; in(u...);}
void out(){cout << "\n";} template <typename T,class... U> void out(const T &t,const U &...u){ cout << t; if(sizeof...(u)) cout << " "; out(u...);}
template<typename T>void die(T x){out(x); exit(0);}
#ifdef NyaanDebug
  #include "NyaanDebug.h"
  #define trc(...) do { cerr << #__VA_ARGS__ << " = "; dbg_out(__VA_ARGS__);} while(0)
  #define trca(v,N) do { cerr << #v << " = "; array_out(v , N);cout << endl;} while(0)
#else
  #define trc(...)
  #define trca(...)
  int main(){solve();}
#endif
using P = pair<int,int>; using vp = vector<P>;
constexpr int MOD = /**/ 1000000007; //*/ 998244353;
//////////

void solve(){
  inl(N , K);
  ll nya = N * (N + 1) / 2;
  if(nya % K != 0) die("No");

  if(K == 1){
    vi v(N); iota(all(v) , 1);  
    out("Yes");
    out(v);
    exit(0);
  }

  // odd
  if(N % 2 == 1){
    if(N == K) die("No");
    out("Yes");
      
    vvi v(K + 1);
    rep(i , N / (2 * K)){
      rep1(j , K) v[j].pb(i * 2 * K + j);
      rep1(j , K) v[K+1-j].pb(i * 2 * K + K + j); 
    }
    // 先頭だけ調整
    rep1(i , K){
      v[i][0] = (i-1)*2%K+1;
    }
    vl s(K + 1 , 0);
    rep1(i,K) each(x,v[i]) s[i]+=x;
    trc(s);
    vi ord(K); iota(all(ord),1);
    sort(all(ord),[&](int a,int b){return s[a]<s[b];});

    rep(i,K) {
      cout << v[ord[i]];
      cout <<" " << (N - i) << endl;
    }
     
  }
  else{
    // even
    out("Yes");
    vvi v(K + 1);
    rep(i , N / (2 * K)){
      rep1(j , K) v[j].pb(i * 2 * K + j);
      rep1(j , K) v[K+1-j].pb(i * 2 * K + K + j); 
    }
    rep1(i,K) out(v[i]);
  }
}