# SPDX-FileCopyrightText: © 2025 Tenstorrent USA, Inc.
# SPDX-License-Identifier: Apache-2.0

import torch
import torch.nn.functional as F
from torch import Tensor

# Backward compatibility: filter_none moved to models.common.sampling._utils
from models.common.sampling._utils import filter_none  # noqa: F401

# Backward compatibility: LogProbsCalculator moved to models.common.sampling.tt_log_probs
from models.common.sampling.tt_log_probs import LogProbsCalculator  # noqa: F401


def top_k_top_p_filtering(
    logits: Tensor,
    top_k: int = 0,
    top_p: float = 1.0,
    filter_value: float = -float("Inf"),
    min_tokens_to_keep: int = 1,
) -> Tensor:
    """Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
    Args:
        logits: logits distribution shape (batch size, vocabulary size)
        if top_k > 0: keep only top k tokens with highest probability (top-k filtering).
        if top_p < 1.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering).
            Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
        Make sure we keep at least min_tokens_to_keep per batch example in the output
    From: https://gist.github.com/thomwolf/1a5a29f6962089e871b94cbd09daf317
    """
    if top_k > 0:
        top_k = min(max(top_k, min_tokens_to_keep), logits.size(-1))  # Safety check
        # Remove all tokens with a probability less than the last token of the top-k
        indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
        logits[indices_to_remove] = filter_value

    if top_p < 1.0:
        sorted_logits, sorted_indices = torch.sort(logits, descending=True)
        cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)

        # Remove tokens with cumulative probability above the threshold (token with 0 are kept)
        sorted_indices_to_remove = cumulative_probs > top_p
        if min_tokens_to_keep > 1:
            # Keep at least min_tokens_to_keep (set to min_tokens_to_keep-1 because we add the first one below)
            sorted_indices_to_remove[..., :min_tokens_to_keep] = 0
        # Shift the indices to the right to keep also the first token above the threshold
        sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
        sorted_indices_to_remove[..., 0] = 0

        # scatter sorted tensors to original indexing
        indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
        logits[indices_to_remove] = filter_value
    return logits