#include <bits/stdc++.h>
using namespace std::literals::string_literals;
using i64 = std::int_fast64_t;
using std::cout;
using std::cerr;
using std::endl;
using std::cin;

template<typename T>
std::vector<T> make_v(size_t a){return std::vector<T>(a);}

template<typename T,typename... Ts>
auto make_v(size_t a,Ts... ts){
  return std::vector<decltype(make_v<T>(ts...))>(a,make_v<T>(ts...));
}

int main() {
	i64 n, k; scanf("%lld%lld", &n, &k);

	if(n == 1 and k == 1) {
		printf("Yes\n");
		printf("1\n");
		return 0;
	}

	i64 tmp = n / k, latte = n * (n + 1) >> 1;
	if(((tmp & 1) and !(k & 1)) or (tmp == 1)) {
		printf("No\n");
		return 0;
	}
	
	int i = 1;
	std::vector<std::vector<int>> ans(k);
	while(tmp) {
		if(tmp & 1) {
			i--;
			int cnt = 0;
			for(int j = 1; j <= (k + 1) / 2; j++) {
				ans[cnt].push_back(i + (k - 2 * (j - 1)));
				ans[cnt].push_back(i + (k + (k + 1) / 2 + j - 1));
				ans[cnt].push_back(i + (2 * k + j));
				cnt++;
			}
			for(int j = (k + 1) / 2 + 1; j <= k; j++) {
				ans[cnt].push_back(i + (k - 1 - 2 * (j - (k + 1) / 2 - 1)));
				ans[cnt].push_back(i + (1 * k + j - (k + 1) / 2));
				ans[cnt].push_back(i + (2 * k + j));
				cnt++;
			}

			i += 3 * k + 1;
			tmp -= 3;
		} else {
			for(int j = 0; j < k; j++) ans[j].push_back(i++);
			for(int j = 0; j < k; j++) ans[k - j - 1].push_back(i++);

			tmp -= 2;
		}
	}
	
	printf("Yes\n");
	for(auto v: ans) {
		for(auto e: v) printf("%d ", e);
		printf("\n");
	}
	return 0;
}