#include <bits/stdc++.h>
// created [2019/12/04] 23:59:42
#pragma GCC diagnostic ignored "-Wsign-compare"
#pragma GCC diagnostic ignored "-Wsign-conversion"

using i32 = int32_t;
using i64 = int64_t;
using u32 = uint32_t;
using u64 = uint64_t;
using uint = unsigned int;
using usize = std::size_t;
using ll = long long;
using ull = unsigned long long;
using ld = long double;
template<typename T> constexpr T popcount(const T u) { return u ? static_cast<T>(__builtin_popcountll(static_cast<u64>(u))) : static_cast<T>(0); }
template<typename T> constexpr T log2p1(const T u) { return u ? static_cast<T>(64 - __builtin_clzll(static_cast<u64>(u))) : static_cast<T>(0); }
template<typename T> constexpr T msbp1(const T u) { return log2p1(u); }
template<typename T> constexpr T lsbp1(const T u) { return __builtin_ffsll(u); }
template<typename T> constexpr T clog(const T u) { return u ? log2p1(u - 1) : static_cast<T>(u); }
template<typename T> constexpr bool ispow2(const T u) { return u and (static_cast<u64>(u) & static_cast<u64>(u - 1)) == 0; }
template<typename T> constexpr T ceil2(const T u) { return static_cast<T>(1) << clog(u); }
template<typename T> constexpr T floor2(const T u) { return u == 0 ? static_cast<T>(0) : static_cast<T>(1) << (log2p1(u) - 1); }
template<typename T> constexpr bool btest(const T mask, const usize ind) { return static_cast<bool>((static_cast<u64>(mask) >> ind) & static_cast<u64>(1)); }
template<typename T> void bset(T& mask, const usize ind) { mask |= (static_cast<T>(1) << ind); }
template<typename T> void breset(T& mask, const usize ind) { mask &= ~(static_cast<T>(1) << ind); }
template<typename T> void bflip(T& mask, const usize ind) { mask ^= (static_cast<T>(1) << ind); }
template<typename T> void bset(T& mask, const usize ind, const bool b) { (b ? bset(mask, ind) : breset(mask, ind)); }
template<typename T> constexpr T bcut(const T mask, const usize ind) { return ind == 0 ? static_cast<T>(0) : static_cast<T>((static_cast<u64>(mask) << (64 - ind)) >> (64 - ind)); }
template<typename T> bool chmin(T& a, const T& b) { return (a > b ? a = b, true : false); }
template<typename T> bool chmax(T& a, const T& b) { return (a < b ? a = b, true : false); }
constexpr unsigned int mod                  = 1000000007;
template<typename T> constexpr T inf_v      = std::numeric_limits<T>::max() / 4;
template<typename Real> constexpr Real pi_v = Real{3.141592653589793238462643383279502884};

template<typename T>
T read()
{
    T v;
    return std::cin >> v, v;
}
template<typename T, typename... Args>
auto read(const usize size, Args... args)
{
    std::vector<decltype(read<T>(args...))> ans(size);
    for (usize i = 0; i < size; i++) { ans[i] = read<T>(args...); }
    return ans;
}
template<typename... Types>
auto reads() { return std::tuple<std::decay_t<Types>...>{read<Types>()...}; }
#    define SHOW(...) static_cast<void>(0)
constexpr ull TEN(const usize n) { return n == 0 ? 1ULL : TEN(n - 1) * 10ULL; }

template<typename T>
std::vector<T> make_v(const usize size, const T v) { return std::vector<T>(size, v); }
template<typename... Args>
auto make_v(const usize size, Args... args) { return std::vector<decltype(make_v(args...))>(size, make_v(args...)); }
int main()
{
    const int N = read<int>();
    const int K = read<int>();
    if ((N / K) % 2 == 1 and N % 2 == 0) { return std::cout << "No" << std::endl, 0; }
    const int M = N / K;
    if (M == 1) { return std::cout << "No" << std::endl, 0; }
    std::cout << "Yes" << std::endl;
    std::vector<std::vector<int>> ans(K);
    auto three = [&]() {
        const int L = (K-1)/2;
        std::vector<int> vs(3*K);
        for(int i=0;i<K;i++){
            vs[i]=i;
        }
        vs[K]= K+2*L;
        for(int i=K+1;i<3*K;i++){
            vs[i]=vs[i-1]+(i%2==0?K:-K-1);
        }
        for(int i=0;i<3*K;i++){
            ans[i%K].push_back(vs[i]);
        }
    };
    if (M % 2 == 0) {
        // 昇順/降順 交互
        for (int i = 0; i < M; i++) {
            std::vector<int> r(K);
            for (int j = 0; j < K; j++) { r[j] = i * K + j; }
            if (i % 2 == 1) { std::reverse(r.begin(), r.end()); }
            for (int j = 0; j < K; j++) { ans[j].push_back(r[j]); }
        }
    } else {
        assert(K % 2 == 1);
        // 3段あればOK
        three();
        // 他の段は昇順/降順 交互
        for (int i = 3; i < M; i++) {
            std::vector<int> r(K);
            for (int j = 0; j < K; j++) { r[j] = i * K + j; }
            if (i % 2 == 1) { std::reverse(r.begin(), r.end()); }
            for (int j = 0; j < K; j++) { ans[j].push_back(r[j]); }
        }
    }
    for (int i = 0; i < K; i++) {
        for (int j = 0; j < M; j++) { std::cout << ans[i][j] + 1 << " "; }
        std::cout << std::endl;
    }

    return 0;
}