import std.stdio, std.conv, std.functional, std.string;
import std.algorithm, std.array, std.container, std.range, std.typecons;
import std.bigint, std.numeric, std.math, std.random;
import core.bitop;

string FMT_F = "%.10f";

static File _f;
void file_io(string fn) { _f = File(fn, "r"); }
static string[] s_rd;
T _RD(T = long)() { while(!s_rd.length) s_rd = readln.chomp.split; string res = s_rd[0]; s_rd.popFront; return res.to!T; }
T _RD(T = long)(File f) { while(!s_rd.length) s_rd = f.readln.chomp.split; string res = s_rd[0]; s_rd.popFront; return res.to!T; }
T[] _RDA(T = long)(T fix = 0) { auto r = readln.chomp.split.to!(T[]); r[] += fix; return r; }
T[] _RDA(T = long)(File f, T fix = 0) { auto r = f.readln.chomp.split.to!(T[]); r[] += fix; return r; }
T RD(T = long)() { if (_f.isOpen) return _RD!T(_f); else return _RD!T; }
T[] RDA(T = long)(T fix = 0) { if (_f.isOpen)  return _RDA!T(_f, fix); else return _RDA!T(fix); }

size_t[] MAKE_IDX(alias less = "a < b", Range)(Range range) { auto idx = new size_t[](range.length); makeIndex!(less)(range, idx); return idx;}
size_t MIN_POS(alias less = "a < b", Range)(Range range) { auto r = minPos!(less)(range); return range.length - r.length; }

void chmin(T)(ref T x, T y) { x = min(x, y); } void chmax(T)(ref T x, T y) { x = max(x, y); }
bool inside(T)(T x, T b, T e) { return x >= b && x < e; }
long lcm(long x, long y) { return x * (y / gcd(x, y)); }

long mod = 10^^9 + 7;
//long mod = 998244353;
//long mod = 1_000_003;
void moda(ref long x, long y) { x = (x + y) % mod; }
void mods(ref long x, long y) { x = ((x + mod) - (y % mod)) % mod; }
void modm(ref long x, long y) { x = (x * y) % mod; }

void main()
{
	auto N = RD;
	auto K = RD;
	auto s = N * (N+1) / 2;
	if (K == 1)
	{
		writeln("Yes");
		long[] ans;
		foreach (i; 0..N)
			ans ~= i+1;
		ans.map!(to!string).join(" ").writeln;
	}
	else if (s % K)
		writeln("No");
	else
	{
		auto cnt = N / K;
		if (cnt % 2 == 0)
		{
			writeln("Yes");
			foreach (i; 0..K)
			{
				long[] ans;
				foreach (j; 0..cnt/2)
				{
					ans ~= i+j*K+1;
				}
				foreach (j; cnt/2..cnt)
				{
					ans ~= (K-i)+j*K;
				}
				ans.map!(to!string).join(" ").writeln;
			}
		}
		else
		{
			if (cnt <= 2)
				writeln("No");
			else
			{
				writeln("Yes");
				foreach (i; 0..K)
				{
					long[] ans;
					auto half = 3 * (cnt / 3);
					if (cnt % 3 == 1) half -= 3;
					foreach (j; 0..half)
					{
						auto pat = j % 3;
						if (pat == 0)
							ans ~= i+j*K+1;
						else if (pat == 1)
							ans ~= (i+K/2)%K+j*K+1;
						else
						{
							auto pos = K-i*2;
							if (pos < 0) pos += K;
							ans ~= pos+j*K;
						}
					}
					foreach (j; half..(half+cnt)/2)
					{
						ans ~= i+j*K+1;
					}
					foreach (j; (half+cnt)/2..cnt)
					{
						ans ~= (K-i)+j*K;
					}
					ans.map!(to!string).join(" ").writeln;
				}
			}
		}
	}

	stdout.flush;
	debug readln;
}