"""Quick test: run the working test_fmha_v3.py with n=256 to check multi-tile."""
import torch, cutlass, cutlass.cute as cute, cutlass.utils as utils, cutlass.pipeline as pipeline
from cutlass.cute.nvgpu import cpasync, tcgen05
from cutlass import Float32, BFloat16, Int32, Boolean, const_expr
from cutlass.utils import LayoutEnum
from cutlass.utils.tmem_allocator import find_tmem_tensor_col_offset
import cuda.bindings.driver as cuda
import cutlass.torch as ct
import math

HEAD_DIM = 64

# Import the working kernel class
import sys
sys.path.insert(0, '/root/dsv4-nvfp4-workspace/kernel')
from tests.unit.test_fmha_v3 import FmhaV3

for n in [128, 256]:
    torch.manual_seed(42)
    m, hd = 128, HEAD_DIM
    q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
    k = torch.randn(n, hd, 1, dtype=torch.bfloat16, device='cuda')
    v = torch.ones(n, hd, dtype=torch.bfloat16, device='cuda')  # V=ones like the working test
    v_kernel = v.unsqueeze(-1)
    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')

    qf = q[:, :, 0].float()
    kf = k[:, :, 0].float()
    scale = 1.0 / math.sqrt(hd)
    attn = qf @ kf.T * scale
    attn = torch.softmax(attn, dim=-1)
    ref = attn @ v.float()

    mQ = ct.from_dlpack(q).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q))
    mK = ct.from_dlpack(k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k))
    mV = ct.from_dlpack(v_kernel).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_kernel))
    mC = ct.from_dlpack(c).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c))
    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)

    kernel = FmhaV3(s_k=n)
    print(f'n={n}: Compiling...', flush=True)
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream)
    compiled(mQ, mK, mV, mC, stream)
    torch.cuda.synchronize()

    out = c[:, :, 0].float()
    cos = torch.nn.functional.cosine_similarity(
        out.flatten().unsqueeze(0), ref.flatten().unsqueeze(0)
    ).item()
    print(f'FMHA v3 n={n}: cos {cos:.6f}  {"PASS" if cos >= 0.99 else "FAIL"}')
    if cos < 0.99:
        print(f'  out[0,:4]={out[0,:4].tolist()}')
        print(f'  ref[0,:4]={ref[0,:4].tolist()}')