#include<bits/stdc++.h>

 using namespace std;

 typedef long long ll;

 typedef unsigned int uint;

 typedef unsigned long long ull;

 typedef pair<int,int> PII;

 typedef pair<ll,ll> Pll;

 typedef vector<int> VI;

 typedef vector<PII> VII;

 //typedef pair<ll,ll>P;

 #define N  1000010

 #define M  200010

 #define fi first

 #define se second

 #define MP make_pair

 #define pb push_back

 #define pi acos(-1)

 #define mem(a,b) memset(a,b,sizeof(a))

 #define rep(i,a,b) for(int i=(int)a;i<=(int)b;i++)

 #define per(i,a,b) for(int i=(int)a;i>=(int)b;i--)

 #define lowbit(x) x&(-x)

 #define Rand (rand()*(1<<16)+rand())

 #define id(x) ((x)<=B?(x):m-n/(x)+1)

 #define ls p<<1

 #define rs p<<1|1

 const int MOD=1e9+,inv2=(MOD+)/;

       double eps=1e-;

       int INF=1e9;

       int inf=0x7fffffff;

       int dx[]={-,,,};

       int dy[]={,,-,};

 VI c[N];

 int read()

 {

    int v=,f=;

    char c=getchar();

    while(c<||<c) {if(c=='-') f=-; c=getchar();}

    while(<=c&&c<=) v=(v<<)+v+v+c-,c=getchar();

    return v*f;

 }

 int main()

 {

     int cas=read();

     while(cas--)

     {

         int n=read(),k=read();

         ll s=1ll*n*(n+)/;

         if(s%k>||k==n&&k>)

         {

             printf("no\n");

             continue;

         }

         printf("yes\n");

         if(n==&&k==)

         {

             printf("1\n");

             continue;

         }

         int t=n/k;

         rep(i,,k) c[i].clear();

         if(t>=&&t%==)

         {

             int x=k/,m=n;

             rep(i,,k)

             {

                 c[i].pb(m);

                 m--;

             }

             rep(i,x+,k)

             {

                 c[i].pb(m);

                 m--;

             }

             rep(i,,x)

             {

                 c[i].pb(m);

                 m--;

             }

             int y=m;

             per(i,k,x+)

             {

                 c[i].pb(m);

                 m-=;

             }

             m=y-;

             per(i,x,)

             {

                 c[i].pb(m);

                 m-=;

             }

             n-=*k;

         }

         t=;

         rep(i,,n/)

         {

             t++;

             if(t==k+) t=;

             c[t].pb(i);

         }

         t=;

         per(i,n,n/+)

         {

             t++;

             if(t==k+) t=;

             c[t].pb(i);

         }

         rep(i,,k)

         {

             rep(j,,(int)c[i].size()-) printf("%d ",c[i][j]);

             printf("\n");

         }

     }

     return ;

 }