"""Replay direct Qwen against an immutable per-layer Comfy trace."""

import argparse
from pathlib import Path

import torch

from h3_blackwell_runtime.qwen3vl_text import Qwen3VL32BTextEncoder


parser = argparse.ArgumentParser()
parser.add_argument("--trace-dir", type=Path, required=True)
parser.add_argument("--checkpoint", default="/text-encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors")
args = parser.parse_args()

encoder = Qwen3VL32BTextEncoder(args.checkpoint).eval()
hidden = torch.load(args.trace_dir / "qwen_input_embeds.pt", map_location="cuda", weights_only=False).to(encoder.dtype)

with torch.inference_mode():
    for index, layer in enumerate(encoder.layers):
        hidden = layer(hidden)
        expected = torch.load(args.trace_dir / "qwen_layers" / f"{index:02d}.pt", map_location="cuda", weights_only=False)
        delta = (hidden.float() - expected.float()).abs()
        print(f"layer={index:02d} max_abs={delta.max().item():.6g} mean_abs={delta.mean().item():.6g}")
    expected = torch.load(args.trace_dir / "qwen_layer50.pt", map_location="cuda", weights_only=False)
    delta = (hidden.float() - expected.float()).abs()
    print(f"layer50 max_abs={delta.max().item():.6g} mean_abs={delta.mean().item():.6g}")