# Single-GPU round-trip
uv run python examples/conversion/hf_megatron_roundtrip.py \
    --hf-model-id <org>/<model>

# Multi-GPU with TP=2
uv run python -m torch.distributed.run --nproc_per_node=2 \
    examples/conversion/hf_megatron_roundtrip_multi_gpu.py \
    --hf-model-id <org>/<model> --tp 2

# Multi-GPU with PP=2
uv run python -m torch.distributed.run --nproc_per_node=2 \
    examples/conversion/hf_megatron_roundtrip_multi_gpu.py \
    --hf-model-id <org>/<model> --pp 2

from megatron.bridge.models.conversion.utils import weights_verification_table
weights_verification_table(bridge, hf_pretrained, megatron_model)

# Compare logits (loads both HF and Megatron models)
uv run python -m torch.distributed.run --nproc_per_node=2 \
    examples/conversion/compare_hf_and_megatron/compare.py \
    --hf_model_path <org>/<model> --tp 2 \
    --prompt "The capital of France is"

uv run python -m torch.distributed.run --nproc_per_node=2 \
    examples/conversion/hf_to_megatron_generate_text.py \
    --hf_model_path <org>/<model> --tp 2 \
    --prompt "The capital of France is" --max_new_tokens 50

import torch


def compare_tensors(a, b, name=""):
    """Compare two tensors and report similarity metrics."""
    max_diff = (a - b).abs().max().item()
    mean_diff = (a - b).abs().mean().item()
    cos_sim = torch.nn.functional.cosine_similarity(
        a.flatten().float(), b.flatten().float(), dim=0,
    ).item()
    print(f"{name}: max_diff={max_diff:.6e}, mean_diff={mean_diff:.6e}, cosine_sim={cos_sim:.8f}")
    return max_diff, mean_diff, cos_sim


def compare_state_dicts(sd_a, sd_b, prefix=""):
    """Compare two state dicts key-by-key, reporting per-parameter differences."""
    keys_a, keys_b = set(sd_a.keys()), set(sd_b.keys())
    missing, extra = keys_a - keys_b, keys_b - keys_a
    if missing:
        print(f"{prefix}Missing keys: {sorted(missing)}")
    if extra:
        print(f"{prefix}Extra keys: {sorted(extra)}")
    max_diffs = {}
    for key in sorted(keys_a & keys_b):
        diff = (sd_a[key].float() - sd_b[key].float()).abs().max().item()
        if diff > 0:
            max_diffs[key] = diff
            print(f"{prefix}{key}: max_diff={diff:.6e}")
    if not max_diffs and not missing and not extra:
        print(f"{prefix}All {len(keys_a & keys_b)} parameters match exactly.")
    return missing, extra, max_diffs