#include<bits/stdc++.h>
using namespace std;
#define ll long long
#define y1 jiajia
#pragma GCC optimize(2)
#pragma GCC optimize(3)
#pragma GCC optimize("Ofast")
#pragma GCC optimize("inline")
#pragma GCC optimize("unroll-loops")
int clr[205][205];
int cnt = 1;
int head[405];
struct edge {
	int v, nxt;
	ll w;
} a[400005];
void add_edge(int u, int v, ll w) {
	++cnt;
	a[cnt].v = v;
	a[cnt].w = w;
	a[cnt].nxt = head[u];
	head[u] = cnt;
}
int flr[405];
int cur[405];
bool bfs(int s, int t) {
	queue<int> q; q.push(s);
	memset(flr, 0, sizeof(flr));
	flr[s] = 1;
	while (!q.empty()) {
		int u = q.front(); q.pop();
		cur[u] = head[u];
		for (int i = head[u]; i; i = a[i].nxt) {
			if (a[i].w && !flr[a[i].v]) {
				flr[a[i].v] = flr[u] + 1;
				q.push(a[i].v);
			}
		}
	}
	return flr[t] > 0;
}
ll dfs(int u, int t, ll lim) {
	if (u == t) return lim;
	if (!lim) return 0;
	ll sum = 0;
	for (int &i = cur[u]; i; i = a[i].nxt) {
		if (flr[a[i].v] != flr[u] + 1) continue;
		if (a[i].w == 0) continue;
		ll tq = dfs(a[i].v, t, min(lim, a[i].w));
		sum += tq;
		lim -= tq;
		a[i].w -= tq;
		a[i ^ 1].w += tq;
		if (lim == 0) return sum;
	}
	return sum;
}
int cntt[205];
pair<int, int> p[205];
bool hv[205][205];
int main() {
	ios::sync_with_stdio(false); cin.tie(0);
	int T = 1;
	while (T--) {
		memset(hv, 0, sizeof(hv));
		memset(cntt, 0, sizeof(cntt));
		memset(clr, 0, sizeof(clr));
		int n, m; cin >> n >> m;
		for (int i = 1; i < n; i++) {
			for (int j = i + 1; j <= n; j++) {
				cin >> clr[i][j];
				clr[j][i] = clr[i][j];
				cntt[clr[i][j]]++;
				hv[i][clr[i][j]] = hv[j][clr[i][j]] = 1;
			}
		}
		for (int i = 1; i <= n; i++) {
			for (int j = 1; j <= n; j++) {
				for (int k = j + 1; k <= n; k++) {
					if (clr[i][j] == clr[i][k]) {
						cout << "No\n";
						goto end;
					}
				}
			}
		}
		if (m % 2 == 0) {
			cout << "No\n";
			goto end;
		}
		for (int i = n + 1; i <= m + 1; i++) {
			for (int j = 1; j <= m; j++) {
				p[j] = {cntt[j], j};
			}
			sort(p + 1, p + 1 + m);
			vector<int> vec;
			for (int j = 1; j <= i - 1; j++) {
				cntt[p[j].second]++;
				vec.push_back(p[j].second);
			}
			cnt = 1; memset(head, 0, sizeof(head));
			int S = m + m + 1, T = m + m + 2;
			for (auto x : vec) {
				add_edge(S, x, 1);
				add_edge(x, S, 0);
			}
			for (int j = 1; j < i; j++) {
				add_edge(j + m, T, 1);
				add_edge(T, j + m, 0);
				for (auto x : vec) {
					if (!hv[j][x]) {
						add_edge(x, j + m, 1);
						add_edge(j + m, x, 0);
					}
				}
			}
			int ans = 0;
			while (bfs(S, T)) ans += dfs(S, T, i - 1);
			if (ans != i - 1) {
				cout << "No\n";
				goto end;
			}
			for (int j = 1; j < i; j++) {
				for (int k = head[j + m]; k; k = a[k].nxt) {
					if (a[k].w == 1 && a[k].v <= m) {
						clr[j][i] = clr[i][j] = a[k].v;
						hv[i][a[k].v] = hv[j][a[k].v] = 1;
					}
				}
			}
		}
		cout << "Yes\n";
		for (int i = 1; i <= m; i++) {
			for (int j = i + 1; j <= m + 1; j++) {
				if (j == m + 1) cout << clr[i][j] << '\n';
				else cout << clr[i][j] << ' ';
			}
		}
		end:;
	}
	return 0;
}