//#define NDEBUG
#include <algorithm>
#include <cstddef>
#include <cstdint>
#include <iostream>
#include <utility>
#include <vector>

namespace n91 {

using i8 = std::int_fast8_t;
using i32 = std::int_fast32_t;
using i64 = std::int_fast64_t;
using u8 = std::uint_fast8_t;
using u32 = std::uint_fast32_t;
using u64 = std::uint_fast64_t;
using isize = std::ptrdiff_t;
using usize = std::size_t;

struct rep {
  struct itr {
    usize i;
    constexpr itr(const usize i) noexcept : i(i) {}
    void operator++() noexcept { ++i; }
    constexpr usize operator*() const noexcept { return i; }
    constexpr bool operator!=(const itr x) const noexcept { return i != x.i; }
  };
  const itr f, l;
  constexpr rep(const usize f, const usize l) noexcept
      : f(std::min(f, l)), l(l) {}
  constexpr auto begin() const noexcept { return f; }
  constexpr auto end() const noexcept { return l; }
};
struct revrep {
  struct itr {
    usize i;
    constexpr itr(const usize i) noexcept : i(i) {}
    void operator++() noexcept { --i; }
    constexpr usize operator*() const noexcept { return i; }
    constexpr bool operator!=(const itr x) const noexcept { return i != x.i; }
  };
  const itr f, l;
  constexpr revrep(const usize f, const usize l) noexcept
      : f(l - 1), l(std::min(f, l) - 1) {}
  constexpr auto begin() const noexcept { return f; }
  constexpr auto end() const noexcept { return l; }
};
template <class T> auto md_vec(const usize n, const T &value) {
  return std::vector<T>(n, value);
}
template <class... Args> auto md_vec(const usize n, Args... args) {
  return std::vector<decltype(md_vec(args...))>(n, md_vec(args...));
}
template <class T> constexpr T difference(const T &a, const T &b) noexcept {
  if (a < b) {
    return b - a;
  } else {
    return a - b;
  }
}
template <class T> void chmin(T &a, const T &b) noexcept {
  if (b < a) {
    a = b;
  }
}
template <class T> void chmax(T &a, const T &b) noexcept {
  if (a < b) {
    a = b;
  }
}
template <class F> class fix_point : private F {
public:
  explicit constexpr fix_point(F &&f) : F(std::forward<F>(f)) {}

  template <class... Args>
  constexpr decltype(auto) operator()(Args &&... args) const {
    return F::operator()(*this, std::forward<Args>(args)...);
  }
};
template <class F> constexpr decltype(auto) make_fix(F &&f) {
  return fix_point<F>(std::forward<F>(f));
}
template <class T> T scan() {
  T ret;
  std::cin >> ret;
  return ret;
}

} // namespace n91

#include <algorithm>
#include <iostream>
#include <utility>

namespace n91 {

void main_() {
  /*
  std::ios::sync_with_stdio(false);
  std::cin.tie(nullptr);
  //*/
  const usize n = scan<usize>();
  const usize k = scan<usize>();
  if (n / k % 2 != 0 && (n + 1) % 2 != 0) {
    std::cout << "No" << std::endl;
    return;
  }
  if (n / k % 2 == 0) {
    std::cout << "Yes" << std::endl;
    auto ans = md_vec(k, 0, usize());
    for (const usize i : rep(0, n)) {
      if (i / k % 2 == 0) {
        ans[i % k].push_back(i);
      } else {
        ans[k - 1 - i % k].push_back(i);
      }
    }
    for (const auto &v : ans) {
      for (const auto e : v) {
        std::cout << e + 1 << ' ';
      }
      std::cout << std::endl;
    }
  } else {
    if (k <= n / k) {
      std::cout << "Yes" << std::endl;
      auto ans = md_vec(k, 0, usize());
      for (const usize i : rep(0, n - k * k)) {
        if (i / k % 2 == 0) {
          ans[i % k].push_back(i);
        } else {
          ans[k - 1 - i % k].push_back(i);
        }
      }
      {
        usize c = 0;
        for (const usize i : rep(n - k * k, n)) {
          ans[c % k].push_back(i);
          c += 1;
          if (i % k == k - 1) {
            c += 1;
          }
        }
      }
      for (const auto &v : ans) {
        for (const auto e : v) {
          std::cout << e + 1 << ' ';
        }
        std::cout << std::endl;
      }
      return;
    }
    if (k == n) {
      std::cout << "No" << std::endl;
      return;
    }
    std::cout << "Yes" << std::endl;
    auto ans = md_vec(k, 0, usize());
    for (const usize i : rep(0, n - k * 3)) {
      if (i / k % 2 == 0) {
        ans[i % k].push_back(i);
      } else {
        ans[k - 1 - i % k].push_back(i);
      }
    }
    {
      std::vector<usize> v(k * 3);
      for (const usize i : rep(0, k * 3)) {
        v[i] = i;
      }
      std::reverse(v.begin() + k, v.begin() + k * 2);
      {
        usize l = 1;
        usize r = 0;
        for (const usize i : rep(1, k / 2 + 1)) {
          if (i % 2 == 1) {
            r += 2;
          } else {
            l += 2;
          }
        }
        usize i = 0;
        r = l;
        l = l - 1;
        while (i != l) {
          std::swap(v[i], v[l]);
          i += 1;
          l -= 1;
        }
        i = k - 1;
        while (r < i) {
          std::swap(v[r], v[i]);
          r += 1;
          i -= 1;
        }
      }
      for (const usize i : rep(0, k)) {
        v[k * 2 + i] = k * 2 + (k / 2) + 2 * k - 1 - v[i] - v[k + i];
        ans[i].push_back(n - k * 3 + v[i]);
        ans[i].push_back(n - k * 3 + v[k + i]);
        ans[i].push_back(n - k * 3 + v[2 * k + i]);
      }
    }
    for (const auto &v : ans) {
      for (const auto e : v) {
        std::cout << e + 1 << ' ';
      }
      std::cout << std::endl;
    }
  }
}

} // namespace n91

int main() {
  n91::main_();
  return 0;
}