"""Compare every direct H3 block output with one ComfyUI per-block capture."""

import torch

from h3_blackwell_runtime.checkpoint import H3Checkpoint
from h3_blackwell_runtime.denoiser import H3PackedDenoiser
from h3_blackwell_runtime.rope import h3_rope_rotation


capture_dir = "/artifacts/capture"
inputs = torch.load(f"{capture_dir}/input.pt", map_location="cuda", weights_only=False)
checkpoint = H3Checkpoint("/models/minimax_h3_ref2va_pruned_nvfp4.safetensors")
model = H3PackedDenoiser.from_checkpoint(checkpoint).eval()

hidden = inputs["hidden"]
rotation = h3_rope_rotation(inputs["position_ids"], model.backbone.inv_freq, hidden.dtype)
with torch.inference_mode():
    for index, (block, adaln) in enumerate(zip(model.backbone.blocks, model.backbone.adaln, strict=True)):
        hidden = block(hidden, rotation, *adaln(inputs["timesteps"]), inputs["segments"])
        expected = torch.load(f"{capture_dir}/blocks/{index:02d}.pt", map_location="cuda", weights_only=False)
        delta = (hidden.float() - expected.float()).abs()
        print(f"block={index:02d} max_abs={delta.max().item():.6g} mean_abs={delta.mean().item():.6g}")