#include <bits/stdc++.h>
using namespace std;
using lint = long long int;
using pint = pair<int, int>;
using plint = pair<lint, lint>;
struct fast_ios { fast_ios(){ cin.tie(0); ios::sync_with_stdio(false); cout << fixed << setprecision(20); }; } fast_ios_;
#define ALL(x) (x).begin(), (x).end()
#define FOR(i, begin, end) for(int i=(begin),i##_end_=(end);i<i##_end_;i++)
#define IFOR(i, begin, end) for(int i=(end)-1,i##_begin_=(begin);i>=i##_begin_;i--)
#define REP(i, n) FOR(i,0,n)
#define IREP(i, n) IFOR(i,0,n)
template<typename T> void ndarray(vector<T> &vec, int len) { vec.resize(len); }
template<typename T, typename... Args> void ndarray(vector<T> &vec, int len, Args... args) { vec.resize(len); for (auto &v : vec) ndarray(v, args...); }
template<typename T> bool chmax(T &m, const T q) { if (m < q) {m = q; return true;} else return false; }
template<typename T> bool chmin(T &m, const T q) { if (m > q) {m = q; return true;} else return false; }
template<typename T1, typename T2> pair<T1, T2> operator+(const pair<T1, T2> &l, const pair<T1, T2> &r) { return make_pair(l.first + r.first, l.second + r.second); }
template<typename T1, typename T2> pair<T1, T2> operator-(const pair<T1, T2> &l, const pair<T1, T2> &r) { return make_pair(l.first - r.first, l.second - r.second); }
template<typename T> istream &operator>>(istream &is, vector<T> &vec){ for (auto &v : vec) is >> v; return is; }
template<typename T> ostream &operator<<(ostream &os, const vector<T> &vec){ os << "["; for (auto v : vec) os << v << ","; os << "]"; return os; }
template<typename T> ostream &operator<<(ostream &os, const deque<T> &vec){ os << "deq["; for (auto v : vec) os << v << ","; os << "]"; return os; }
template<typename T> ostream &operator<<(ostream &os, const set<T> &vec){ os << "{"; for (auto v : vec) os << v << ","; os << "}"; return os; }
template<typename T> ostream &operator<<(ostream &os, const unordered_set<T> &vec){ os << "{"; for (auto v : vec) os << v << ","; os << "}"; return os; }
template<typename T> ostream &operator<<(ostream &os, const multiset<T> &vec){ os << "{"; for (auto v : vec) os << v << ","; os << "}"; return os; }
template<typename T> ostream &operator<<(ostream &os, const unordered_multiset<T> &vec){ os << "{"; for (auto v : vec) os << v << ","; os << "}"; return os; }
template<typename T1, typename T2> ostream &operator<<(ostream &os, const pair<T1, T2> &pa){ os << "(" << pa.first << "," << pa.second << ")"; return os; }
template<typename TK, typename TV> ostream &operator<<(ostream &os, const map<TK, TV> &mp){ os << "{"; for (auto v : mp) os << v.first << "=>" << v.second << ","; os << "}"; return os; }
template<typename TK, typename TV> ostream &operator<<(ostream &os, const unordered_map<TK, TV> &mp){ os << "{"; for (auto v : mp) os << v.first << "=>" << v.second << ","; os << "}"; return os; }
#define dbg(x) cerr << #x << " = " << (x) << " (L" << __LINE__ << ") " << __FILE__ << endl;
/*
#include <ext/pb_ds/assoc_container.hpp>
#include <ext/pb_ds/tree_policy.hpp>
#include <ext/pb_ds/tag_and_trait.hpp>
using namespace __gnu_pbds; // find_by_order(), order_of_key()
template<typename TK> using pbds_set = tree<TK, null_type, less<TK>, rb_tree_tag, tree_order_statistics_node_update>;
template<typename TK, typename TV> using pbds_map = tree<TK, TV, less<TK>, rb_tree_tag, tree_order_statistics_node_update>;
*/

// 1-indexed BIT (i : [1, len])
template <typename T>
struct BIT : std::vector<T>
{
    BIT(int len = 0) : std::vector<T>(len + 1) {}
    void reset() { fill(this->begin(), this->end(), 0); }
    void add(int pos, T v) {
        while (pos > 0 and pos < (int)this->size()) (*this)[pos] += v, pos += pos & -pos;
    }
    T sum(int pos) const { // (0, pos]
        T res = 0;
        while (pos > 0) res += (*this)[pos], pos -= pos & -pos;
        return res;
    }
    friend std::ostream &operator<<(std::ostream &os, const BIT &bit) {
        T prv = 0;
        os << '[';
        for (int i = 1; i < (int)bit.size(); i++) {
            T now = bit.sum(i);
            os << now - prv << ",";
            prv = now;
        }
        os << ']';
        return os;
    }
};

template <typename T>
vector<T> z(vector<T> v)
{
    vector<T> ls = v;
    sort(ALL(ls));
    ls.erase(unique(ALL(ls)), ls.end());
    for (auto &x : v) x = lower_bound(ALL(ls), x) - ls.begin() + 1;
    return v;
}

template <typename T>
lint calc_tentou(vector<T> v)
{
    v = z(v);
    BIT<int> bit(v.size() + 1);
    lint ret = 0;
    for (auto x : v)
    {
        ret += bit.sum(v.size() + 1) - bit.sum(x);
        bit.add(x, 1);
    }
    return ret;
}

lint calc(vector<vector<int>> mat)
{
    vector<lint> t;
    for (auto v : mat) t.emplace_back(calc_tentou(v));
    lint ret = calc_tentou(t);
    int H = mat.size(), W = mat[0].size();
    t.clear();
    REP(j, W)
    {
        vector<int> ww(H);
        REP(i, H) ww[i] = mat[i][j];
        t.emplace_back(calc_tentou(ww));
    }
    ret += calc_tentou(t);
    return ret;
}

vector<vector<int>> solve(int N, int K)
{
    vector mat(N, vector<int>(N));

    int i = 0, j = 0;
    while (i < N and j < N)
    {
        int a = N - 1 - i + N - 1 - j;
        if (i == N - 2 and j == N - 2 and K == 1)
        {
            mat[i][j] = mat[i + 1][j] = mat[i + 1][j + 1] = 1;
            i += 2, j += 2;
            continue;
        }

        if (a <= K)
        {
            K -= a;
            mat[i][j] = 1;
            i++, j++;
        }
        else
        {
            if (i < j)
                i++;
            else
                j++;
        }
    }
    return mat;
}

int main()
{
    vector<lint> v{5, 5, 4, 3};

    int N, K;
    cin >> N >> K;
    // N = 10;
    // REP(K, 100)
    // {
    //     auto mat = solve(N, K);
    // }
    auto mat = solve(N, K);
    lint cmat = calc(mat);
    // if (cmat != K)
    // {
    //     dbg(mat);
    //     dbg((plint(cmat, K)));
    // }

    if (cmat != K)
    {
        puts("No");
    }
    else
    {
        cout << "Yes" << '\n';
        for (auto vec : mat)
        {
            for (auto x : vec) cout << x << ' ';
            cout << '\n';
        }
    }
}