update files to remove sparse attention usage for the 0.5B model

modeling_minicpm.py

@@ -24,7 +24,7 @@ import torch.utils.checkpoint
 from torch import nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 from transformers.activations import ACT2FN
-from transformers.cache_utils import Cache, DynamicCache
+from transformers.cache_utils import Cache, DynamicCache, CacheLayerMixin, DynamicLayer
 from transformers.modeling_attn_mask_utils import (
     AttentionMaskConverter,
     _prepare_4d_attention_mask,
@@ -52,493 +52,9 @@ from .configuration_minicpm import MiniCPMConfig
 try:
     from flash_attn import flash_attn_func, flash_attn_varlen_func
     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
-    from infllm_v2 import (
-        infllmv2_attn_stage1,
-        infllmv2_attn_varlen_func,
-        infllmv2_attn_with_kvcache,
-        max_pooling_1d,
-    )
 except:
     pass
 
-from functools import lru_cache
-
-
-def compressed_attention(
-    q: torch.Tensor,
-    k: torch.Tensor,
-    v: torch.Tensor,
-    kernel_size: int,
-    kernel_stride: int,
-    block_size: int,
-    topk: int,
-    cu_seqlens_q: torch.Tensor,
-    cu_seqlens_k: torch.Tensor,
-    max_seqlen_q: int,
-    max_seqlen_k: int,
-    sm_scale: float = None,
-    init_blocks: int = 1,
-    local_blocks: int = 2,
-    parallel_topk_compute: Union[str, bool] = 'auto',
-    total_seq_lens=-1,
-) -> Tuple[torch.Tensor, torch.Tensor]:
-    """Attention between query and compressed key and value. Compute attention output and topk block idx used in topk_sparse_attention.
-
-    Args:
-        q (torch.Tensor): shape [total_q_len, num_q_heads, head_dim]
-        k (torch.Tensor): shape [total_kv_len, num_kv_heads, head_dim]
-        v (torch.Tensor): shape [total_kv_len, num_kv_heads, head_dim]
-        kernel_size (int): kernel size in compress_key_value
-        kernel_stride (int): stride of compress_key_value
-        block_size (int): key value block size for topk sparse attention.
-        topk (int): number of blocks for each query.
-        cu_seqlens_q (torch.Tensor): shape [batch_size + 1], similar to cu_seqlens_q in flash_attn_func_varlen.
-        cu_seqlens_k (torch.Tensor): shape [batch_size + 1], similar to cu_seqlens_k in flash_attn_func_varlen.
-        max_seqlen_q (int): max q len of the batch.
-        max_seqlen_k (int): max k len of the batch.
-        sm_scale (float, optional): softmax scale. Defaults to None, means 1/sqrt(head_dim).
-        init_blocks (int, optional): Number of init blocks for each query. Defaults to 1.
-        local_blocks (int, optional): Number of local blocks for each query. Defaults to 2.
-        parallel_topk_compute (str, optional): Only set it to False when the sequence length is too long. This can avoid a current bug.
-            We'll fix this issue later. Defaults to auto, it will be set to False when the sequence length is greater than 32k and True otherwise.
-
-    Returns:
-        Tuple[torch.Tensor, torch.Tensor]: attention output and topk_idx used in topk_sparse_attention
-    """
-    with torch.no_grad():
-        cache_len = 0
-        batch_size = cu_seqlens_q.shape[0] - 1
-        if total_seq_lens == -1:
-            total_seq_lens = max_seqlen_q
-            q_idx = torch.cat(
-                [
-                    torch.arange(cu_seqlens_q[i + 1] - cu_seqlens_q[i], device=q.device) + total_seq_lens - (cu_seqlens_q[i + 1] - cu_seqlens_q[i])
-                    for i in range(batch_size)
-                ],
-                dim=0,
-            )
-            q_idx = q_idx // block_size
-
-        else:
-            cache_len = total_seq_lens - max_seqlen_q
-            assert batch_size == 1, 'batch_size must be 1 when total_seq_lens is set'
-            q_idx = torch.tensor([total_seq_lens - 1], device=q.device, dtype=torch.int32) // block_size
-
-        score = infllmv2_attn_stage1(
-            q.contiguous(),
-            k.contiguous(),
-            v.contiguous(),
-            cu_seqlens_q=cu_seqlens_q,
-            cu_seqlens_k=cu_seqlens_k,
-            max_seqlen_q=max_seqlen_q,
-            max_seqlen_k=max_seqlen_k,
-            causal=q_idx.shape[0] > 1)
-        score = score[:, :q_idx.shape[0], :]
-
-        # Replace transform_score with max_pooling_1d
-        block_score = max_pooling_1d(
-            score.contiguous(),
-            cache_len=cache_len,
-            local_blocks=local_blocks,
-            init_blocks=init_blocks,
-            block_size=block_size,
-            stride=kernel_stride,
-        )
-        # get topk
-        topk = min(topk, block_score.shape[-1])
-        topk_idx = block_score.topk(topk, dim=-1).indices.sort(-1).values
-        topk_idx[topk_idx >= q_idx[None, :, None]] = -1
-        topk_idx = topk_idx.to(torch.int32)
-
-    return topk_idx
-
-
-@lru_cache(maxsize=16)
-def calc_chunks_with_stride(cu_seqlen, chunk_size, kernel_stride):
-    """
-    Compute the chunks that require Sparse attention, with stride support.
-
-    Args:
-        cu_seqlen (torch.Tensor): Cumulative sequence lengths for each sample.
-        chunk_size (int): Chunk size used for Sparse attention.
-        kernel_stride (int): Stride size when sliding over the sequence.
-
-    Returns:
-        filtered_indices (torch.Tensor): Indices used to directly index into the key/value tensors.
-        cu_seqlens_compressed (torch.Tensor): Cumulative sequence lengths after compression.
-    """
-    # 1. Compute the length of each sequence
-    batch_sizes = cu_seqlen[1:] - cu_seqlen[:-1]
-
-    # 2. Compute the start positions of chunks for each sequence (with stride)
-    max_seq_len = torch.max(batch_sizes)
-    max_num_chunks_per_seq = (max_seq_len - chunk_size) // kernel_stride + 1
-    chunk_start_offsets = torch.arange(0, max_num_chunks_per_seq * kernel_stride, kernel_stride, device=cu_seqlen.device)
-    seq_starts = cu_seqlen[:-1]
-    chunk_start_in_seq = seq_starts[:, None] + chunk_start_offsets[None, :]  # [batch_size, max_num_chunks_per_seq]
-
-    # 3. Filter out chunks that exceed sequence length or are smaller than the full chunk size
-    chunk_end_in_seq = chunk_start_in_seq + chunk_size
-    valid_chunk_mask = (chunk_end_in_seq <= (seq_starts[:, None] + batch_sizes[:, None]))
-
-    # 4. Filter valid chunk start positions using the valid_chunk_mask
-    valid_chunk_starts = chunk_start_in_seq[valid_chunk_mask]  # [num_valid_chunks]
-    del chunk_start_in_seq
-    # 5. Generate filtered_indices
-    chunk_indices = torch.arange(
-        0, chunk_size, device=cu_seqlen.device
-    )[None, :]  # [1, chunk_size]
-    filtered_indices = valid_chunk_starts[:, None] + chunk_indices  # [num_valid_chunks, chunk_size]
-    filtered_indices = filtered_indices.view(-1)  # Flatten to 1D indices
-
-    # 6. Compute compressed cumulative sequence lengths
-    num_filtered_chunks_per_batch = valid_chunk_mask.sum(dim=1)  # Number of valid chunks per batch
-    cu_seqlens_compressed = torch.zeros(
-        len(cu_seqlen), dtype=torch.int32, device=cu_seqlen.device
-    )
-    cu_seqlens_compressed[1:] = num_filtered_chunks_per_batch.cumsum(dim=0)
-    del num_filtered_chunks_per_batch, chunk_start_offsets, seq_starts, chunk_end_in_seq, valid_chunk_mask, chunk_indices
-    return filtered_indices, cu_seqlens_compressed
-
-
-class CompressK(torch.nn.Module):
-    def __init__(self, head_num_k, head_dim, kernel_size, kernel_stride=16):
-        """
-        Module for compressing key (K) representations.
-
-        Args:
-            head_num_k (int): Number of key attention heads.
-            head_dim (int): Dimension of each attention head.
-            kernel_size (int): Size of each chunk used for compression.
-            kernel_stride (int, optional): Stride used when dividing input into chunks. Default is 16.
-        """
-        super().__init__()
-        self.kernel_size = kernel_size
-        self.head_num_k = head_num_k
-        self.head_dim = head_dim
-        self.kernel_stride = kernel_stride
-
-    def forward(self, k: torch.Tensor, cu_seqlens):
-        """
-        Forward pass for compressing the key (K) tensor.
-
-        Args:
-            k (torch.Tensor): Input key tensor of shape (total_seq_len, num_heads, head_dim).
-            cu_seqlens (torch.Tensor): Cumulative sequence lengths for each sample in the batch, typically used for handling variable-length sequences.
-
-        Returns:
-            compress_k (torch.Tensor): Compressed key tensor.
-            cu_seqlens_compressed (torch.Tensor): Updated cumulative sequence lengths after compression.
-
-        """
-        # Compute chunk-related metadata, with stride support
-        filtered_k_indices, cu_seqlens_compressed = calc_chunks_with_stride(
-            cu_seqlens, self.kernel_size, self.kernel_stride
-        )
-
-        # Extract filtered key vectors
-        filtered_k = k.index_select(0, filtered_k_indices.view(-1))
-
-        # split
-        filtered_k = filtered_k.view(filtered_k.shape[0] // self.kernel_size, self.kernel_size, self.head_num_k, self.head_dim)  # [l, block_size,h,d]
-
-        compressed_k = filtered_k.mean(dim=1)
-        return compressed_k, cu_seqlens_compressed
-
-
-class DynamicCacheQKV(DynamicCache):
-    """
-    A cache that grows dynamically as more tokens are generated. This is the default for generative models.
-
-    It stores the Key and Value states as a list of tensors, one for each layer. The expected shape for each tensor is
-    `[batch_size, num_heads, seq_len, head_dim]`.
-
-    Example:
-        ```python
-        >>> from transformers import AutoTokenizer, AutoModelForCausalLM, DynamicCache
-
-        >>> model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
-        >>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
-
-        >>> inputs = tokenizer(text="My name is Qwen2", return_tensors="pt")
-
-        >>> # Prepare a cache class and pass it to model's forward
-        >>> past_key_values = DynamicCache()
-        >>> outputs = model(**inputs, past_key_values=past_key_values, use_cache=True)
-        >>> outputs.past_key_values # access cache filled with key/values from generation
-        DynamicCache()
-        ```
-    """
-    def __init__(self, num_hidden_layers: Optional[int] = None) -> None:
-        super().__init__()
-        if num_hidden_layers is None:
-            self.key_cache: List[torch.Tensor] = []
-            self.value_cache: List[torch.Tensor] = []
-            self.compress_k_cache: List[torch.Tensor] = []
-            self.no_compress_k_cache: List[torch.Tensor] = []
-            self.cached_compressed_cu_seqlens: List[torch.Tensor] = []
-            self.no_rope_key_cache: List[torch.Tensor] = []
-        else:
-            self.key_cache: List[torch.Tensor] = [[] for _ in range(num_hidden_layers)]
-            self.value_cache: List[torch.Tensor] = [[] for _ in range(num_hidden_layers)]
-            self.compress_k_cache: List[torch.Tensor] = [[] for _ in range(num_hidden_layers)]
-            self.no_compress_k_cache: List[torch.Tensor] = [[] for _ in range(num_hidden_layers)]
-            self.cached_compressed_cu_seqlens: List[torch.Tensor] = [[] for _ in range(num_hidden_layers)]
-            self.no_rope_key_cache: List[torch.Tensor] = [[] for _ in range(num_hidden_layers)]
-        self._seen_tokens = 0  # Used in `generate` to keep tally of how many tokens the cache has seen
-
-    def __getitem__(self, layer_idx: int) -> List[Tuple[torch.Tensor]]:
-        """
-        Support for backwards-compatible `past_key_value` indexing, e.g. `past_key_value[0][0].shape[2]` to get the
-        sequence length.
-        """
-        if layer_idx < len(self):
-            return (self.key_cache[layer_idx], self.value_cache[layer_idx])
-        else:
-            raise KeyError(f'Cache only has {len(self)} layers, attempted to access layer with index {layer_idx}')
-
-    def __iter__(self):
-        """
-        Support for backwards-compatible `past_key_value` iteration, e.g. `for x in past_key_value:` to iterate over
-        keys and values
-        """
-        for layer_idx in range(len(self)):
-            yield (self.key_cache[layer_idx], self.value_cache[layer_idx])
-
-    def __len__(self):
-        """
-        Support for backwards-compatible `past_key_value` length, e.g. `len(past_key_value)`. This value corresponds
-        to the number of layers in the model.
-        """
-        return len(self.key_cache)
-
-    def update(
-        self,
-        key_states: torch.Tensor,
-        value_states: torch.Tensor,
-        layer_idx: int,
-        cache_kwargs: Optional[Dict[str, Any]] = None
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        """
-        Updates the cache with the new `key_states` and `value_states` for the layer `layer_idx`.
-
-        Parameters:
-            key_states (`torch.Tensor`):
-                The new key states to cache.
-            value_states (`torch.Tensor`):
-                The new value states to cache.
-            layer_idx (`int`):
-                The index of the layer to cache the states for.
-            cache_kwargs (`Dict[str, Any]`, `optional`):
-                Additional arguments for the cache subclass. No additional arguments are used in `DynamicCache`.
-
-        Return:
-            A tuple containing the updated key and value states.
-        """
-        # Update the number of seen tokens
-        if layer_idx == 0:
-            self._seen_tokens += key_states.shape[-2]
-
-        # Update the cache
-        if len(self.key_cache) <= layer_idx:
-            self.key_cache.append(key_states)
-            self.value_cache.append(value_states)
-
-        # content on layer cache can be a tensor and checking not tensor causes errors
-        # so we explicitly check for the empty list
-        elif self.key_cache[layer_idx] == []:
-            self.key_cache[layer_idx] = key_states
-            self.value_cache[layer_idx] = value_states
-
-        else:
-            self.key_cache[layer_idx] = torch.cat([self.key_cache[layer_idx], key_states], dim=-2)
-            self.value_cache[layer_idx] = torch.cat([self.value_cache[layer_idx], value_states], dim=-2)
-        return self.key_cache[layer_idx], self.value_cache[layer_idx]
-
-    def update_no_rope_key(
-            self,
-            key_states: torch.Tensor,
-            layer_idx: int,
-            cache_kwargs: Optional[Dict[str, Any]] = None):
-
-        # Update the cache
-        if len(self.no_rope_key_cache) <= layer_idx:
-            self.no_rope_key_cache.append(key_states)
-
-        # content on layer cache can be a tensor and checking not tensor causes errors
-        # so we explicitly check for the empty list
-        elif self.no_rope_key_cache[layer_idx] == []:
-            self.no_rope_key_cache[layer_idx] = key_states
-        else:
-            self.no_rope_key_cache[layer_idx] = torch.cat([self.no_rope_key_cache[layer_idx], key_states], dim=1)
-        return self.no_rope_key_cache[layer_idx]
-
-    def update_compress_k(
-        self,
-        key_states: torch.Tensor,
-        layer_idx: int,
-        cache_kwargs: Optional[Dict[str, Any]] = None
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        """
-        Updates the cache with the new `key_states` and `value_states` for the layer `layer_idx`.
-
-        Parameters:
-            key_states (`torch.Tensor`):
-                The new key states to cache.
-            value_states (`torch.Tensor`):
-                The new value states to cache.
-            layer_idx (`int`):
-                The index of the layer to cache the states for.
-            cache_kwargs (`Dict[str, Any]`, `optional`):
-                Additional arguments for the cache subclass. No additional arguments are used in `DynamicCache`.
-
-        Return:
-            A tuple containing the updated key and value states.
-        """
-
-        # Update the cache
-        if len(self.compress_k_cache) <= layer_idx:
-            self.compress_k_cache.append(key_states)
-
-        # content on layer cache can be a tensor and checking not tensor causes errors
-        # so we explicitly check for the empty list
-        elif self.compress_k_cache[layer_idx] == []:
-            self.compress_k_cache[layer_idx] = key_states
-        else:
-            self.compress_k_cache[layer_idx] = torch.cat([self.compress_k_cache[layer_idx], key_states], dim=0)
-        return self.compress_k_cache[layer_idx]
-
-    def update_no_compress_k(
-        self,
-        key_states: torch.Tensor,
-        layer_idx: int,
-        kernel_size: int = 32,
-        kernel_stride: int = 16,
-        cache_kwargs: Optional[Dict[str, Any]] = None
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        """
-        Updates the cache with the new `key_states` and `value_states` for the layer `layer_idx`.
-
-        Parameters:
-            key_states (`torch.Tensor`):
-                The new key states to cache.
-            value_states (`torch.Tensor`):
-                The new value states to cache.
-            layer_idx (`int`):
-                The index of the layer to cache the states for.
-            cache_kwargs (`Dict[str, Any]`, `optional`):
-                Additional arguments for the cache subclass. No additional arguments are used in `DynamicCache`.
-
-        Return:
-            A tuple containing the updated key and value states.
-        """
-        # Update the cache
-        if len(self.no_compress_k_cache) <= layer_idx:
-            self.no_compress_k_cache.append(key_states)
-
-        # content on layer cache can be a tensor and checking not tensor causes errors
-        # so we explicitly check for the empty list
-        elif self.no_compress_k_cache[layer_idx] == []:
-            self.no_compress_k_cache[layer_idx] = key_states
-        else:
-            self.no_compress_k_cache[layer_idx] = torch.cat([self.no_compress_k_cache[layer_idx], key_states], dim=0)
-
-        current_len = self.no_compress_k_cache[layer_idx].shape[0]
-
-        if current_len >= kernel_size:
-            k_chunk = self.no_compress_k_cache[layer_idx][:kernel_size]
-            self.no_compress_k_cache[layer_idx] = self.no_compress_k_cache[layer_idx][kernel_stride:]
-            return k_chunk
-        else:
-            return None
-
-    def get_seq_length(self, layer_idx: Optional[int] = 0) -> int:
-        """Returns the sequence length of the cached states. A layer index can be optionally passed."""
-        # TODO: deprecate this function in favor of `cache_position`
-        if len(self.key_cache) <= layer_idx or (len(self.key_cache) > layer_idx and self.key_cache[layer_idx] == []):
-            return 0
-        return self.key_cache[layer_idx].shape[-2]
-
-    def get_max_length(self) -> Optional[int]:
-        """Returns the maximum sequence length of the cached states. DynamicCache does not have a maximum length."""
-        return None
-
-    def to_legacy_cache(self) -> Tuple[Tuple[torch.Tensor], Tuple[torch.Tensor]]:
-        """Converts the `DynamicCache` instance into the its equivalent in the legacy cache format. Used for
-        backward compatibility."""
-        legacy_cache = ()
-        for layer_idx in range(len(self)):
-            legacy_cache += ((self.key_cache[layer_idx], self.value_cache[layer_idx]),)
-        return legacy_cache
-
-    # @classmethod
-    # def from_legacy_cache(
-    #     cls, past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, num_hidden_layers: int = None
-    # ) -> "DynamicCacheQKV":
-    #     """Converts a cache in the legacy cache format into an equivalent `DynamicCache`. Used for
-    #     backward compatibility."""
-    #     cache = cls(num_hidden_layers)
-    #     if past_key_values is not None:
-    #         for layer_idx in range(len(past_key_values)):
-    #             key_states, value_states, query_status = past_key_values[layer_idx]
-    #             cache.update(key_states, value_states, query_status,layer_idx)
-    #     return cache
-
-    def crop(self, max_length: int):
-        """Crop the past key values up to a new `max_length` in terms of tokens. `max_length` can also be
-        negative to remove `max_length` tokens. This is used in assisted decoding and contrastive search."""
-        # In case it is negative
-        if max_length < 0:
-            max_length = self.get_seq_length() - abs(max_length)
-
-        if self.get_seq_length() <= max_length:
-            return
-
-        self._seen_tokens = max_length
-        for idx in range(len(self.key_cache)):
-            if self.key_cache[idx] != []:
-                self.key_cache[idx] = self.key_cache[idx][..., :max_length, :]
-                self.value_cache[idx] = self.value_cache[idx][..., :max_length, :]
-
-    def batch_split(self, full_batch_size: int, split_size: int, num_hidden_layers: int) -> List['DynamicCacheQKV']:
-        """Split the current instance into a list of `DynamicCache` by the batch size. This will be used by
-        `_split_model_inputs()` in `generation.utils`"""
-        out = []
-        for i in range(0, full_batch_size, split_size):
-            current_split = DynamicCacheQKV(num_hidden_layers)
-            current_split._seen_tokens = self._seen_tokens
-            current_split.key_cache = [tensor[i: i + split_size] for tensor in self.key_cache]
-            current_split.value_cache = [tensor[i: i + split_size] for tensor in self.value_cache]
-            out.append(current_split)
-        return out
-
-    @classmethod
-    def from_batch_splits(cls, splits: List['DynamicCacheQKV'], num_hidden_layers: int) -> 'DynamicCacheQKV':
-        """This is the opposite of the above `batch_split()` method. This will be used by `stack_model_outputs` in
-        `generation.utils`"""
-        cache = cls(num_hidden_layers)
-        for idx in range(len(splits[0])):
-            key_cache = [current.key_cache[idx] for current in splits if current.key_cache[idx] != []]
-            value_cache = [current.key_cache[idx] for current in splits if current.key_cache[idx] != []]
-            query_cache = [current.key_cache[idx] for current in splits if current.key_cache[idx] != []]
-            if key_cache != []:
-                layer_keys = torch.cat(key_cache, dim=0)
-                layer_values = torch.cat(value_cache, dim=0)
-                layer_query = torch.cat(query_cache, dim=0)
-                cache.update(layer_keys, layer_values, idx, query_states=layer_query)
-        return cache
-
-    def batch_repeat_interleave(self, repeats: int):
-        """Repeat the cache `repeats` times in the batch dimension. Used in contrastive search."""
-        for layer_idx in range(len(self)):
-            self.key_cache[layer_idx] = self.key_cache[layer_idx].repeat_interleave(repeats, dim=0)
-            self.value_cache[layer_idx] = self.value_cache[layer_idx].repeat_interleave(repeats, dim=0)
-
-    def batch_select_indices(self, indices: torch.Tensor):
-        """Only keep the `indices` in the batch dimension of the cache. Used in contrastive search."""
-        for layer_idx in range(len(self)):
-            self.key_cache[layer_idx] = self.key_cache[layer_idx][indices, ...]
-            self.value_cache[layer_idx] = self.value_cache[layer_idx][indices, ...]
 
 
 # This makes `_prepare_4d_causal_attention_mask` a leaf function in the FX graph.
@@ -567,22 +83,6 @@ def _get_unpad_data(attention_mask):
     )
 
 
-def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
-    warnings.warn(
-        'Calling `transformers.models.minicpm.modeling_minicpm._prepare_4d_attention_mask` is deprecated and will be removed in v4.37. Use `transformers.modeling_attn_mask_utils._prepare_4d_attention_mask'
-    )
-    return _prepare_4d_attention_mask(mask=mask, dtype=dtype, tgt_len=tgt_len)
-
-
-def _make_causal_mask(
-    input_ids_shape: torch.Size, dtype: torch.dtype, device: torch.device, past_key_values_length: int = 0
-):
-    warnings.warn(
-        'Calling `transformers.models.minicpm.modeling_minicpm._make_causal_mask` is deprecated and will be removed in v4.37. Use `transformers.models.minicpm.modeling_minicpm.AttentionMaskConverter._make_causal_mask'
-    )
-    return AttentionMaskConverter._make_causal_mask(
-        input_ids_shape=input_ids_shape, dtype=dtype, device=device, past_key_values_length=past_key_values_length
-    )
 
 
 # @torch.jit.script  # type: ignore
@@ -796,6 +296,21 @@ class MiniCPMMLP(nn.Module):
 
         return down_proj
 
+def _unpad_one_tensor(hidden_states, attention_mask):
+    # Unpad the hidden states using the indices
+    indices, cu_seqlens, max_seqlen_in_batch = _get_unpad_data(attention_mask)
+    batch_size, seq_len = hidden_states.shape[:2]
+    
+    # Get the remaining dimensions
+    remaining_dims = hidden_states.shape[2:]
+    
+    # Reshape to (batch_size * seq_len, *remaining_dims)
+    reshaped_states = hidden_states.reshape(batch_size * seq_len, *remaining_dims)
+    
+    # Apply unpadding using indices
+    unpadded_states = index_first_axis(reshaped_states, indices)
+    
+    return unpadded_states, indices, cu_seqlens, max_seqlen_in_batch
 
 def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
     """
@@ -927,15 +442,7 @@ class MiniCPMAttention(nn.Module):
         key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
         value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
 
-        kv_seq_len = key_states.shape[-2]
-        if past_key_value is not None:
-            if self.layer_idx is None:
-                raise ValueError(
-                    f'The cache structure has changed since version v4.36. If you are using {self.__class__.__name__} '
-                    'for auto-regressive decoding with k/v caching, please make sure to initialize the attention class '
-                    'with a layer index.'
-                )
-            kv_seq_len += past_key_value.get_usable_length(kv_seq_len, self.layer_idx)
+        kv_seq_len = position_ids.max().item() + 1
         cos, sin = self.rotary_emb(value_states.to(torch.float32), seq_len=kv_seq_len)
 
         query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
@@ -1037,9 +544,7 @@ class MiniCPMFlashAttention2(MiniCPMAttention):
         key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
         value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
 
-        kv_seq_len = key_states.shape[-2]
-        if past_key_value is not None:
-            kv_seq_len += past_key_value.get_usable_length(kv_seq_len, self.layer_idx)
+        kv_seq_len = position_ids.max().item() + 1
         cos, sin = self.rotary_emb(value_states.to(torch.float32), seq_len=kv_seq_len)
         query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
 
@@ -1187,504 +692,6 @@ class MiniCPMFlashAttention2(MiniCPMAttention):
         )
 
 
-class MiniCPMInfLLMv2Attention(MiniCPMAttention):
-    """
-    MiniCPM flash attention module. This module inherits from `MiniCPMAttention` as the weights of the module stays
-    untouched. The only required change would be on the forward pass where it needs to correctly call the public API of
-    flash attention and deal with padding tokens in case the input contains any of them.
-    """
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        assert self.config._attn_implementation == 'flash_attention_2', 'Only flash_attention_2 is supported for sparse attention'
-        # TODO: Should be removed once Flash Attention for RoCm is bumped to 2.1.
-        # flash_attn<2.1 generates top-left aligned causal mask, while what is needed here is bottom-right alignment, that was made default for flash_attn>=2.1. This attribute is used to handle this difference. Reference: https://github.com/Dao-AILab/flash-attention/releases/tag/v2.1.0.
-        # Beware that with flash_attn<2.1, using q_seqlen != k_seqlen (except for the case q_seqlen == 1) produces a wrong mask (top-left).
-        self._flash_attn_uses_top_left_mask = not is_flash_attn_greater_or_equal_2_10()
-
-        #  -------sparse-------
-        self.kernel_size = self.config.sparse_config.get('kernel_size', 32)
-        self.kernel_stride = self.config.sparse_config.get('kernel_stride', 16)
-        self.init_blocks = self.config.sparse_config.get('init_blocks', 1)
-        self.block_size = self.config.sparse_config.get('block_size', 64)
-        self.window_size = self.config.sparse_config.get('window_size', 2048)
-        self.dense_len = self.config.sparse_config.get('dense_len', 8192)
-
-        self.local_blocks = self.window_size // self.block_size  # local_blocks
-        self.topk = self.config.sparse_config.get('topk', 64)
-        self.use_nope = self.config.sparse_config.get('use_nope', False)
-        self.compress_k = CompressK(self.num_key_value_heads, self.head_dim, kernel_size=self.kernel_size, kernel_stride=self.kernel_stride)
-
-    def forward(
-        self,
-        hidden_states: torch.Tensor,
-        attention_mask: Optional[torch.LongTensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_value: Optional[Cache] = None,
-        output_attentions: bool = False,
-        use_cache: bool = False,
-        **kwargs,
-    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
-        # MiniCPMFlashAttention2 attention does not support output_attentions
-        if 'padding_mask' in kwargs:
-            warnings.warn(
-                'Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`'
-            )
-
-            # overwrite attention_mask with padding_mask
-            attention_mask = kwargs.pop('padding_mask')
-
-        output_attentions = False
-
-        bsz, q_len, _ = hidden_states.size()
-        assert bsz == 1, 'Only batch_size=1 is supported at the moment.'
-
-        query_states = self.q_proj(hidden_states)
-        key_states = self.k_proj(hidden_states)
-        value_states = self.v_proj(hidden_states)
-
-        # !save no rope
-        if self.use_nope:
-            query_states_no_rope = query_states.view(bsz, q_len, self.num_heads, self.head_dim)
-            key_states_no_rope = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim)
-
-        # Flash attention requires the input to have the shape
-        # batch_size x seq_length x head_dim x hidden_dim
-        # therefore we just need to keep the original shape
-        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
-        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
-        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
-
-        kv_seq_len = key_states.shape[-2]
-        if past_key_value is not None:
-            kv_seq_len += past_key_value.get_usable_length(kv_seq_len, self.layer_idx)
-        cos, sin = self.rotary_emb(value_states.to(torch.float32), seq_len=kv_seq_len)
-        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
-
-        if past_key_value is not None:
-            cache_kwargs = {'sin': sin, 'cos': cos}  # Specific to RoPE models
-            key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
-
-        # TODO: These transpose are quite inefficient but Flash Attention requires the layout [batch_size, sequence_length, num_heads, head_dim]. We would need to refactor the KV cache
-        # to be able to avoid many of these transpose/reshape/view.
-        query_states = query_states.transpose(1, 2)
-        key_states = key_states.transpose(1, 2)
-        value_states = value_states.transpose(1, 2)
-        if self.use_nope:
-            no_rope_param = {
-                'key_states_no_rope': key_states_no_rope,
-                'query_states_no_rope': query_states_no_rope,
-            }
-            if kv_seq_len <= self.dense_len:
-                past_key_value.update_no_rope_key(key_states_no_rope, self.layer_idx)
-        else:
-            no_rope_param = None
-
-        dropout_rate = self.attention_dropout if self.training else 0.0
-
-        # In PEFT, usually we cast the layer norms in float32 for training stability reasons
-        # therefore the input hidden states gets silently casted in float32. Hence, we need
-        # cast them back in the correct dtype just to be sure everything works as expected.
-        # This might slowdown training & inference so it is recommended to not cast the LayerNorms
-        # in fp32. (MiniCPMRMSNorm handles it correctly)
-
-        input_dtype = query_states.dtype
-        if input_dtype == torch.float32:
-            # Handle the case where the model is quantized
-            if hasattr(self.config, '_pre_quantization_dtype'):
-                target_dtype = self.config._pre_quantization_dtype
-            else:
-                target_dtype = self.q_proj.weight.dtype
-
-            logger.warning_once(
-                f'The input hidden states seems to be silently casted in float32, this might be related to'
-                f' the fact you have upcasted embedding or layer norm layers in float32. We will cast back the input in'
-                f' {target_dtype}.'
-            )
-
-            query_states = query_states.to(target_dtype)
-            key_states = key_states.to(target_dtype)
-            value_states = value_states.to(target_dtype)
-        if kv_seq_len < self.dense_len:
-            attn_output = self._flash_attention_forward_dense(
-                query_states, key_states, value_states, attention_mask, q_len, dropout=dropout_rate)
-        elif past_key_value is None or q_len != 1:    # prefilling
-            attn_output = self._flash_attention_forward(
-                query_states, key_states, value_states, attention_mask, q_len, dropout=dropout_rate,
-                no_rope_param=no_rope_param,  # if past_key_value is not None else None,
-                past_key_value=past_key_value)
-        else:
-            attn_output = self._flash_attention_forward_with_kv_cache(
-                query_states, key_states, value_states, attention_mask, q_len, dropout=dropout_rate, no_rope_param=no_rope_param, past_key_value=past_key_value)
-
-        attn_output = attn_output.reshape(bsz, q_len, self.hidden_size).contiguous()
-        attn_output = self.o_proj(attn_output)
-
-        if not output_attentions:
-            attn_weights = None
-
-        return attn_output, attn_weights, past_key_value
-
-    def _flash_attention_forward(
-        self, query_states, key_states, value_states, attention_mask, query_length, dropout=0.0, softmax_scale=None, no_rope_param=None, past_key_value=None
-    ):
-        """
-        Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token
-        first unpad the input, then computes the attention scores and pad the final attention scores.
-
-        Args:
-            query_states (`torch.Tensor`):
-                Input query states to be passed to Flash Attention API
-            key_states (`torch.Tensor`):
-                Input key states to be passed to Flash Attention API
-            value_states (`torch.Tensor`):
-                Input value states to be passed to Flash Attention API
-            attention_mask (`torch.Tensor`):
-                The padding mask - corresponds to a tensor of size `(batch_size, seq_len)` where 0 stands for the
-                position of padding tokens and 1 for the position of non-padding tokens.
-            dropout (`int`, *optional*):
-                Attention dropout
-            softmax_scale (`float`, *optional*):
-                The scaling of QK^T before applying softmax. Default to 1 / sqrt(head_dim)
-        """
-        if not self._flash_attn_uses_top_left_mask:
-            causal = self.is_causal
-        else:
-            # TODO: Remove the `query_length != 1` check once Flash Attention for RoCm is bumped to 2.1. For details, please see the comment in MiniCPMFlashAttention2 __init__.
-            causal = self.is_causal and query_length != 1
-        # Contains at least one padding token in the sequence
-        if attention_mask is not None:
-            batch_size = query_states.shape[0]
-            query_states, key_states, value_states, indices_q, cu_seq_lens, max_seq_lens = self._upad_input(
-                query_states, key_states, value_states, attention_mask, query_length
-            )
-            if no_rope_param is not None:
-                # nope unpad
-                no_rope_param['query_states_no_rope'] = no_rope_param['query_states_no_rope'].squeeze(0)
-                no_rope_param['key_states_no_rope'] = no_rope_param['key_states_no_rope'].squeeze(0)
-
-            cu_seqlens_q, cu_seqlens_k = cu_seq_lens
-            max_seqlen_in_batch_q, max_seqlen_in_batch_k = max_seq_lens
-            attn_output_unpad = self.sparse_forward(
-                query_states,
-                key_states,
-                value_states,
-                cu_seqlens_q,
-                cu_seqlens_k,
-                max_seqlen_in_batch_q,
-                max_seqlen_in_batch_k,
-                no_rope_param=no_rope_param,
-                past_key_value=past_key_value,
-            )
-
-            attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
-        else:
-            raise ValueError('Need attention mask')
-
-        return attn_output
-
-    def _flash_attention_forward_with_kv_cache(
-        self, query_states, key_states, value_states, attention_mask, query_length, dropout=0.0, softmax_scale=None, no_rope_param=None, past_key_value=None
-    ):
-        """
-        Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token
-        first unpad the input, then computes the attention scores and pad the final attention scores.
-
-        Args:
-            query_states (`torch.Tensor`):
-                Input query states to be passed to Flash Attention API
-            key_states (`torch.Tensor`):
-                Input key states to be passed to Flash Attention API
-            value_states (`torch.Tensor`):
-                Input value states to be passed to Flash Attention API
-            attention_mask (`torch.Tensor`):
-                The padding mask - corresponds to a tensor of size `(batch_size, seq_len)` where 0 stands for the
-                position of padding tokens and 1 for the position of non-padding tokens.
-            dropout (`int`, *optional*):
-                Attention dropout
-            softmax_scale (`float`, *optional*):
-                The scaling of QK^T before applying softmax. Default to 1 / sqrt(head_dim)
-        """
-        if not self._flash_attn_uses_top_left_mask:
-            causal = self.is_causal
-        else:
-            # TODO: Remove the `query_length != 1` check once Flash Attention for RoCm is bumped to 2.1. For details, please see the comment in MiniCPMFlashAttention2 __init__.
-            causal = self.is_causal and query_length != 1
-        # Contains at least one padding token in the sequence
-        if attention_mask is not None:
-
-            batch_size = query_states.shape[0]
-
-            # query_states, key_states, value_states, indices_q, cu_seq_lens, max_seq_lens = self._upad_input(
-            #     query_states, key_states, value_states, attention_mask, query_length=query_length
-            # )
-
-            assert batch_size == 1, 'Only batch_size=1 is supported at the moment.'
-            # prepare past kv ,new kv
-            new_q = query_states
-
-            new_k = key_states[:, -1:, :, :].contiguous()
-            new_v = value_states[:, -1:, :, :].contiguous()
-
-            past_k = key_states[:, :-1, :, :].contiguous()
-            past_v = value_states[:, :-1, :, :].contiguous()
-            if no_rope_param is not None:
-                # nope unpad
-                no_rope_param['query_states_no_rope'] = no_rope_param['query_states_no_rope'].squeeze(0)
-                no_rope_param['key_states_no_rope'] = no_rope_param['key_states_no_rope'].squeeze(0)
-
-            attn_output = self.sparse_forward_with_kv_cache(
-                past_k=past_k, past_v=past_v, new_k=new_k, new_v=new_v, new_q=new_q, batch_size=batch_size, no_rope_param=no_rope_param, past_key_value=past_key_value)
-
-            # attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
-        else:
-            raise ValueError('need attention mask')
-
-        return attn_output
-
-    def sparse_forward(self,
-                       query_layer,
-                       key_layer,
-                       value_layer,
-                       cu_seqlens_q,
-                       cu_seqlens_k,
-                       max_seqlen_in_batch_q,
-                       max_seqlen_in_batch_k,
-                       no_rope_param=None,
-                       past_key_value=None):
-        stage1_k = key_layer if no_rope_param is None else no_rope_param['key_states_no_rope']
-        compressed_k, compressed_cu_seqlens = self.compress_k(stage1_k, cu_seqlens_k)
-        compressed_v = compressed_k.clone()
-        if past_key_value is not None:
-            # Compute the start indices of keys (k) that were not compressed, Only batch_size=1 is supported at the moment.
-            no_compress_k_start = compressed_k.shape[0] * self.kernel_stride
-            past_key_value.update_compress_k(
-                compressed_k, self.layer_idx
-            )
-            past_key_value.update_no_compress_k(
-                key_layer[no_compress_k_start:], self.layer_idx, no_compress_k_start)
-            past_key_value.cached_compressed_cu_seqlens.append(compressed_cu_seqlens)
-        compressed_seqlens = compressed_cu_seqlens[1:] - compressed_cu_seqlens[:-1]
-        topk_idx = compressed_attention(
-            query_layer if no_rope_param is None else no_rope_param['query_states_no_rope'],
-            compressed_k,
-            compressed_v,
-            self.kernel_size,
-            self.kernel_stride,
-            self.block_size,
-            self.topk,
-            cu_seqlens_q,
-            compressed_cu_seqlens,
-            max_seqlen_in_batch_q,
-            compressed_seqlens.max().item(),
-            None,
-            init_blocks=self.init_blocks,
-            local_blocks=self.local_blocks,
-        )
-
-        topk_attn_output = infllmv2_attn_varlen_func(
-            query_layer,
-            key_layer,
-            value_layer,
-            cu_seqlens_q,
-            cu_seqlens_k,
-            max_seqlen_in_batch_q,
-            max_seqlen_in_batch_k,
-            dropout_p=0.0,
-            deterministic=False,
-            softmax_scale=None,
-            causal=True,
-            return_attn_probs=False,
-            block_window_size=self.window_size // self.block_size,
-            topk_idx=topk_idx
-        )
-
-        return topk_attn_output
-
-    def sparse_forward_with_kv_cache(self, past_k=None, past_v=None, new_k=None, new_v=None, new_q=None, batch_size=None, no_rope_param=None, past_key_value=None):
-
-        # stage1_k = new_k.squeeze(0) if no_rope_param is None else no_rope_param['key_states_no_rope']
-        if past_k.shape[1] + new_k.shape[1] == self.dense_len and (past_key_value.compress_k_cache == [] or len(past_key_value.compress_k_cache) < self.layer_idx + 1 or past_key_value.compress_k_cache[self.layer_idx] == []):
-            if no_rope_param is not None:
-                stage1_k = past_key_value.no_rope_key_cache[self.layer_idx].squeeze(0).contiguous()  # just batch_size ==1
-            else:
-                stage1_k = torch.cat([past_k, new_k], dim=1).contiguous().squeeze(0).contiguous()  # just batch_size ==1
-            compressed_k, compressed_cu_seqlens = self.compress_k(stage1_k, torch.tensor([0, stage1_k.shape[0]], device=stage1_k.device, dtype=torch.int32))  # just batch_size ==1
-
-            # Compute the start indices of keys (k) that were not compressed, Only batch_size=1 is supported at the moment.
-            no_compress_k_start = compressed_k.shape[0] * self.kernel_stride
-            past_key_value.update_compress_k(
-                compressed_k, self.layer_idx
-            )
-            past_key_value.update_no_compress_k(
-                stage1_k[no_compress_k_start:], self.layer_idx, no_compress_k_start)
-            past_key_value.cached_compressed_cu_seqlens.append(compressed_cu_seqlens)
-
-        else:
-            stage1_k = new_k.squeeze(0) if no_rope_param is None else no_rope_param['key_states_no_rope']
-            no_compress_k = past_key_value.update_no_compress_k(
-                stage1_k, self.layer_idx, kernel_stride=self.kernel_stride, kernel_size=self.kernel_size)
-            if no_compress_k is not None:
-                compressed_k = no_compress_k.mean(dim=0, keepdim=True)  # [1, n_heads_k, head_dim]
-
-                compressed_k = past_key_value.update_compress_k(
-                    compressed_k, self.layer_idx)  # [seqlen, nheads_k, head_dim]
-
-                past_key_value.cached_compressed_cu_seqlens[self.layer_idx][-1] += 1    # !Increment the last entry in sequence lengths by 1; currently supports only batch_size = 1
-                compressed_cu_seqlens = past_key_value.cached_compressed_cu_seqlens[self.layer_idx]
-            else:
-                compressed_k = past_key_value.compress_k_cache[self.layer_idx]  # [seqlen, nheads_k, head_dim]
-                compressed_cu_seqlens = past_key_value.cached_compressed_cu_seqlens[self.layer_idx]
-
-        compressed_v = compressed_k.clone()
-
-        compressed_seqlens = compressed_cu_seqlens[1:] - compressed_cu_seqlens[:-1]
-        torch.cuda.synchronize()
-        # Manually verify that the lengths match
-        assert compressed_k.shape[0] == compressed_seqlens.sum().item(), 'The length of compressed_k does not match the sum of compressed_seqlens'
-        topk_idx = compressed_attention(
-            new_q.squeeze(0).contiguous() if no_rope_param is None else no_rope_param['query_states_no_rope'],
-            compressed_k,
-            compressed_v,
-            self.kernel_size,
-            self.kernel_stride,
-            self.block_size,
-            self.topk,
-            torch.tensor([0, 1], device=compressed_k.device, dtype=torch.int32),
-            compressed_cu_seqlens,
-            1,
-            compressed_seqlens.max().item(),
-            None,
-            init_blocks=self.init_blocks,
-            local_blocks=self.local_blocks,
-            total_seq_lens=past_k.shape[1] + 1,  # !Only batch_size=1 is supported at the moment.
-        )
-
-        repeat_times = 1
-        if repeat_times > 1:
-            new_q = new_q.repeat_interleave(repeat_times, dim=-2)
-        else:
-            new_q = new_q
-
-        cache_batch_idx = torch.arange(batch_size, device=new_q.device, dtype=torch.int32)
-
-        seqlen_k = past_k.shape[1] + new_k.shape[1]  # !Only batch_size=1 is supported at the moment.
-        seqlens_k = torch.full((batch_size,), seqlen_k - 1, dtype=torch.int32, device=new_q.device)
-
-        past_k = torch.cat([past_k, torch.zeros_like(new_k, dtype=new_k.dtype)], dim=1).contiguous()   # Append one zero vector to avoid potential out-of-bounds access
-        past_v = torch.cat([past_v, torch.zeros_like(new_v, dtype=new_v.dtype)], dim=1).contiguous()   # Append one zero vector to avoid potential out-of-bounds access
-        topk_attn_output = infllmv2_attn_with_kvcache(
-            q=new_q,
-            k_cache=past_k,
-            v_cache=past_v,
-            topk_idx=topk_idx,
-            block_window_size=self.window_size // self.block_size,
-            k=new_k,                   # [batch_size, 1, nheads_k, d]
-            v=new_v,                   # [batch_size, 1, nheads_k, d]
-            cache_seqlens=seqlens_k,   # current_seqlens_k-1
-            rotary_cos=None,           # No rotary embeddings
-            rotary_sin=None,           # No rotary embeddings
-            cache_batch_idx=cache_batch_idx,
-            causal=False,              # Renaming to match function signature
-        )
-        return topk_attn_output
-
-    def _flash_attention_forward_dense(
-        self, query_states, key_states, value_states, attention_mask, query_length, dropout=0.0, softmax_scale=None
-    ):
-        """
-        Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token
-        first unpad the input, then computes the attention scores and pad the final attention scores.
-
-        Args:
-            query_states (`torch.Tensor`):
-                Input query states to be passed to Flash Attention API
-            key_states (`torch.Tensor`):
-                Input key states to be passed to Flash Attention API
-            value_states (`torch.Tensor`):
-                Input value states to be passed to Flash Attention API
-            attention_mask (`torch.Tensor`):
-                The padding mask - corresponds to a tensor of size `(batch_size, seq_len)` where 0 stands for the
-                position of padding tokens and 1 for the position of non-padding tokens.
-            dropout (`int`, *optional*):
-                Attention dropout
-            softmax_scale (`float`, *optional*):
-                The scaling of QK^T before applying softmax. Default to 1 / sqrt(head_dim)
-        """
-        if not self._flash_attn_uses_top_left_mask:
-            causal = self.is_causal
-        else:
-            # TODO: Remove the `query_length != 1` check once Flash Attention for RoCm is bumped to 2.1. For details, please see the comment in MiniCPMFlashAttention2 __init__.
-            causal = self.is_causal and query_length != 1
-        # Contains at least one padding token in the sequence
-        if attention_mask is not None:
-            batch_size = query_states.shape[0]
-            query_states, key_states, value_states, indices_q, cu_seq_lens, max_seq_lens = self._upad_input(
-                query_states, key_states, value_states, attention_mask, query_length
-            )
-
-            cu_seqlens_q, cu_seqlens_k = cu_seq_lens
-            max_seqlen_in_batch_q, max_seqlen_in_batch_k = max_seq_lens
-            attn_output_unpad = flash_attn_varlen_func(
-                query_states,
-                key_states,
-                value_states,
-                cu_seqlens_q=cu_seqlens_q,
-                cu_seqlens_k=cu_seqlens_k,
-                max_seqlen_q=max_seqlen_in_batch_q,
-                max_seqlen_k=max_seqlen_in_batch_k,
-                dropout_p=dropout,
-                softmax_scale=softmax_scale,
-                causal=causal,
-            )
-
-            attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
-        else:
-            attn_output = flash_attn_func(
-                query_states, key_states, value_states, dropout, softmax_scale=softmax_scale, causal=causal
-            )
-
-        return attn_output
-
-    def _upad_input(self, query_layer, key_layer, value_layer, attention_mask, query_length):
-        indices_k, cu_seqlens_k, max_seqlen_in_batch_k = _get_unpad_data(attention_mask)
-        batch_size, kv_seq_len, num_key_value_heads, head_dim = key_layer.shape
-
-        key_layer = index_first_axis(
-            key_layer.reshape(batch_size * kv_seq_len, num_key_value_heads, head_dim), indices_k
-        )
-        value_layer = index_first_axis(
-            value_layer.reshape(batch_size * kv_seq_len, num_key_value_heads, head_dim), indices_k
-        )
-        if query_length == kv_seq_len:
-            query_layer = index_first_axis(
-                query_layer.reshape(batch_size * kv_seq_len, self.num_heads, head_dim), indices_k
-            )
-            cu_seqlens_q = cu_seqlens_k
-            max_seqlen_in_batch_q = max_seqlen_in_batch_k
-            indices_q = indices_k
-        elif query_length == 1:
-            max_seqlen_in_batch_q = 1
-            cu_seqlens_q = torch.arange(
-                batch_size + 1, dtype=torch.int32, device=query_layer.device
-            )  # There is a memcpy here, that is very bad.
-            indices_q = cu_seqlens_q[:-1]
-            query_layer = query_layer.squeeze(1)
-        else:
-            # The -q_len: slice assumes left padding.
-            attention_mask = attention_mask[:, -query_length:]
-            query_layer, indices_q, cu_seqlens_q, max_seqlen_in_batch_q = unpad_input(query_layer, attention_mask)
-
-        return (
-            query_layer,
-            key_layer,
-            value_layer,
-            indices_q,
-            (cu_seqlens_q, cu_seqlens_k),
-            (max_seqlen_in_batch_q, max_seqlen_in_batch_k),
-        )
-
-
 class MiniCPMSdpaAttention(MiniCPMAttention):
     """
     MiniCPM attention module using torch.nn.functional.scaled_dot_product_attention. This module inherits from
@@ -1727,9 +734,7 @@ class MiniCPMSdpaAttention(MiniCPMAttention):
         key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
         value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
 
-        kv_seq_len = key_states.shape[-2]
-        if past_key_value is not None:
-            kv_seq_len += past_key_value.get_usable_length(kv_seq_len, self.layer_idx)
+        kv_seq_len = position_ids.max().item() + 1
         cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
 
         query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
@@ -1783,10 +788,7 @@ class MiniCPMDecoderLayer(nn.Module):
     def __init__(self, config: MiniCPMConfig, layer_idx: int):
         super().__init__()
         self.hidden_size = config.hidden_size
-        if config.sparse_config is not None and torch.cuda.is_available():
-            raise NotImplementedError("MiniCPM4-0.5B does not support sparse attention yet.")
-        else:
-            self.self_attn = MINICPM_ATTENTION_CLASSES[config._attn_implementation](config=config, layer_idx=layer_idx)
+        self.self_attn = MINICPM_ATTENTION_CLASSES[config._attn_implementation](config=config, layer_idx=layer_idx)
 
         self.mlp = MiniCPMMLP(config)
         self.input_layernorm = MiniCPMRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
@@ -2052,11 +1054,10 @@ class MiniCPMModel(MiniCPMPreTrainedModel):
                 raise ValueError(
                     'You must use the new past_key_values format, such as the Cache class, instead of the old tuple format.'
                 )
-                past_key_values = DynamicCache.from_legacy_cache(past_key_values)
 
-            past_key_values_length = past_key_values.get_usable_length(seq_length)
-            if self.config.sparse_config is not None and torch.cuda.is_available() and past_key_values_length == 0:
-                past_key_values = DynamicCacheQKV()
+            # Calculate the usable length of past key values
+            past_key_values_length = past_key_values.get_seq_length() if isinstance(past_key_values, Cache) else 0
+
 
         if position_ids is None:
             device = input_ids.device if input_ids is not None else inputs_embeds.device
@@ -2282,12 +1283,16 @@ class MiniCPMForCausalLM(MiniCPMPreTrainedModel):
     ):
         if past_key_values is not None:
             if isinstance(past_key_values, Cache):
+                # Use the new Cache class methods
                 cache_length = past_key_values.get_seq_length()
-                past_length = past_key_values.seen_tokens
-                max_cache_length = None     # past_key_values.get_max_length()
-            else:
-                cache_length = past_length = past_key_values[0][0].shape[2]
+
+                
+                past_length = cache_length
                 max_cache_length = None
+            else:
+                raise ValueError(
+                    'You must use the new past_key_values format, such as the Cache class, instead of the old tuple format.'
+                )
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where