Update modeling_minicpm.py

modeling_minicpm.py

@@ -21,10 +21,10 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 import torch
 import torch.nn.functional as F
 import torch.utils.checkpoint
-from torch import nn
+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,
@@ -47,7 +47,9 @@ from transformers.utils import (
 )
 from transformers.utils.import_utils import is_torch_fx_available
 
-from .configuration_minicpm import MiniCPMConfig
+
+
+from .configuration_minicpm import MiniCPMConfig    #!一定要改
 
 try:
     from flash_attn import flash_attn_func, flash_attn_varlen_func
@@ -57,6 +59,7 @@ try:
         infllmv2_attn_varlen_func,
         infllmv2_attn_with_kvcache,
         max_pooling_1d,
+        max_pooling_1d_varlen
     )
 except:
     pass
@@ -64,184 +67,74 @@ except:
 from functools import lru_cache
 
 
-
-def get_quantizer(quant_type="none", bit=4, group_size=128):
-    if quant_type == "intsym":
-        return SteIntSymQuantizerGPTQ(bit, group_size)
-    elif quant_type == "ternary":
-        return SteTernaryQuantizer(group_size)
-    elif quant_type == "none":
-        return NoQuantizer()
-    else:
-        raise ValueError(f"Unsupported quantization type: {quant_type}")
-
-class SteIntSymQuantizerGPTQ(nn.Module):
-    def __init__(self, bit=4, group_size=-1):
-        super().__init__()
-        self.bit = bit
-        self.group_size = group_size
-
-    def forward(self, x):
-        org_w_shape = x.shape
-
-        if self.group_size > 0:
-            assert org_w_shape[-1] % self.group_size == 0
-            x = x.reshape(-1, self.group_size)
-        elif self.group_size == -1:
-            assert org_w_shape[-1] % self.group_size == 0
-            x = x.reshape(-1, x.shape[-1])
-        elif self.group_size == 0:
-            x = x.reshape(1, -1)
-        
-        assert x.dim() == 2
-
-        xmax = x.max(dim=1, keepdim=True)[0]
-        xmin = x.min(dim=1, keepdim=True)[0]
-        abs_max_val = torch.maximum(torch.abs(xmin), xmax)  # 与Quantizer的xmax计算一致
-        scales = abs_max_val * 2 / (2 ** self.bit - 1)  # 分子分母都对齐
-
-        max_int = 2 ** (self.bit - 1) - 1
-        min_int = - (2 ** (self.bit - 1))
-
-        assert torch.isnan(scales).sum() == 0
-
-        x_q = (torch.clamp(torch.round(x / scales), min_int, max_int)) * scales
-        
-        assert torch.isnan(x_q).sum() == 0
-
-        x = x.reshape(org_w_shape)
-        x_q = x_q.reshape(org_w_shape)
-
-        return x + (x_q - x).detach()
-
-class SteTernaryQuantizer(nn.Module):
-    def __init__(self, group_size):
-        super().__init__()
-        self.group_size = group_size
-
-    def forward(self, x):
-        org_w_shape = x.shape
-        if self.group_size > 0:
-            assert x.shape[-1] % self.group_size == 0
-            x = x.reshape(-1, self.group_size)
-        elif self.group_size == -1:
-            x = x.reshape(-1, x.shape[-1])
-
-        assert x.dim() == 2
-
-        scales = 1.0 / (x.abs().mean(dim=1, keepdim=True).clamp_(min=1e-5))
-        x_q = (torch.clamp(torch.round(x * scales),-1,1) / scales)
-
-        assert torch.isnan(x_q).sum() == 0
-
-        x = x.reshape(org_w_shape)
-        x_q = x_q.reshape(org_w_shape)
-
-        return x + (x_q - x).detach()
-
-class NoQuantizer(nn.Module):
-    def __init__(self):
-        super().__init__()
-
-    def forward(self, x):
-        return x
-
-class LinearQuantizer(nn.Linear):
-    def __init__(self, in_features, out_features, bias=False, quant_type="ternary", bit=4, group_size=-1):
-        super().__init__(in_features, out_features, bias)
-        self.quantizer = get_quantizer(quant_type, bit, group_size)
-    
-    def forward(self, x):
-        weight_tensor = self.quantizer(self.weight)
-        x = torch.nn.functional.linear(x, weight_tensor)
-        if self.bias is not None:
-            x = x + self.bias
-        return x
-
 def compressed_attention(
     q: torch.Tensor,
     k: torch.Tensor,
-    v: torch.Tensor,
+    k2: torch.Tensor,
     kernel_size: int,
     kernel_stride: int,
     block_size: int,
     topk: int,
     cu_seqlens_q: torch.Tensor,
     cu_seqlens_k: torch.Tensor,
+    cu_seqlens_k2: 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,
+    cache_lens=None,
 ) -> 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
-
+        
+        # Check if it's prefilling stage
+        is_prefilling = cache_lens is None or (cache_lens == 0).all().item()
+        
+        if is_prefilling:  # prefilling stage
+            # Calculate q_idx for each query position in each batch
+            cache_lens = torch.zeros(batch_size, dtype=torch.int32, device=q.device) 
+            q_idx = torch.cat([
+                (torch.arange(cu_seqlens_q[i + 1] - cu_seqlens_q[i], device=q.device) + 
+                 max_seqlen_q - (cu_seqlens_q[i + 1] - cu_seqlens_q[i])) // block_size
+                for i in range(batch_size)
+            ], dim=0)  # shape: [total_q_len]
+        else:  # decoding stage
+            # Each batch has only one query (last position)
+            q_idx = cache_lens // block_size  # shape: [batch_size] = [total_q_len] in decoding
+
+        # 计算attention score
         score = infllmv2_attn_stage1(
             q.contiguous(),
             k.contiguous(),
-            v.contiguous(),
+            k2.contiguous(),
             cu_seqlens_q=cu_seqlens_q,
             cu_seqlens_k=cu_seqlens_k,
+            cu_seqlens_v=cu_seqlens_k2,
             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(
+            causal=is_prefilling
+        )
+        score = score[:, :q_idx.shape[0], :]  # [num_heads, total_q_len, num_blocks]
+        
+        block_score = max_pooling_1d_varlen(
             score.contiguous(),
-            cache_len=cache_len,
+            cu_seqlens_q,
+            cu_seqlens_k,
+            cache_lens,
+            max_seqlen_q,
+            max_seqlen_k,
             local_blocks=local_blocks,
             init_blocks=init_blocks,
             block_size=block_size,
-            stride=kernel_stride,
-        )
+            stride=kernel_stride
+        )  # shape: [num_heads, total_q_len, num_blocks]
+        
+
         # 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 > q_idx[None, :, None]] = -1
         topk_idx = topk_idx.to(torch.int32)
 
     return topk_idx
@@ -340,299 +233,133 @@ class CompressK(torch.nn.Module):
         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:
+class InfLLMv2CacheLayer(DynamicLayer):
+    def __init__(self):
         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] = []
+        # Initialize any additional attributes specific to InfLLMv2CacheLayer
+        self.no_rope_keys = torch.tensor([], dtype=torch.float32)
+        self.compress_k_cache = []
+        self.no_compress_k_cache = []
+        self.cached_compressed_cu_seqlens = torch.tensor([], dtype=torch.int32)
+        self.compress_k_cache_varlen = torch.tensor([], dtype=torch.float32)
+        # Add support for compress_k2
+        self.compress_k2_cache = []
+        self.cached_compressed_cu_seqlens2 = torch.tensor([], dtype=torch.int32)
+        self.compress_k2_cache_varlen = torch.tensor([], dtype=torch.float32)
+        self.no_compress_k2_cache = []
+
+    def update_no_rope_key(self, key_states):
+        if self.no_rope_keys.numel() == 0:
+            self.no_rope_keys = key_states
         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])
+            self.no_rope_keys = torch.cat([self.no_rope_keys, key_states], dim=1)
+        return self.no_rope_keys
+
+    def update_compress_k(self, key_states, cu_seqlens=None):
+        if len(self.compress_k_cache) == 0:
+            if cu_seqlens is not None:
+                self.cached_compressed_cu_seqlens = cu_seqlens.clone()
+            self.compress_k_cache_varlen = key_states
+            split_sizes = (cu_seqlens[1:] - cu_seqlens[:-1]).tolist()
+            self.compress_k_cache = list(torch.split(key_states, split_sizes))
         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`.
+            for index, k in enumerate(key_states):
+                if k is not None:
+                    self.compress_k_cache[index] = torch.cat([self.compress_k_cache[index], k], dim=0)
+            new_seq_lens = torch.tensor([tensor.shape[0] for tensor in self.compress_k_cache], dtype=torch.int32)
+            new_cumsum = torch.cumsum(new_seq_lens, dim=0, dtype=torch.int32)
+            
+            self.compress_k_cache_varlen = torch.cat(self.compress_k_cache, dim=0)
+            self.cached_compressed_cu_seqlens = torch.cat([torch.tensor([0], dtype=torch.int32), new_cumsum]).to(self.compress_k_cache_varlen.device)
+        return self.compress_k_cache_varlen, self.cached_compressed_cu_seqlens
+
+    def update_no_compress_k(self, key_states, kernel_size=32, kernel_stride=16):
+        k_chunk_list = []
+        for index, k in enumerate(key_states):
+            if len(self.no_compress_k_cache) <= index:
+                self.no_compress_k_cache.append(k)
+            else:
+                self.no_compress_k_cache[index] = torch.cat([self.no_compress_k_cache[index], k], dim=0)
+                current_len = self.no_compress_k_cache[index].shape[0]
+                if current_len >= kernel_size:
+                    k_chunk_list.append(self.no_compress_k_cache[index][:kernel_size])
+                    self.no_compress_k_cache[index] = self.no_compress_k_cache[index][kernel_stride:]
+                else:
+                    k_chunk_list.append(None)
+        return k_chunk_list
+
+    def update_compress_k2(self, key_states, cu_seqlens=None):
+        if len(self.compress_k2_cache) == 0:
+            if cu_seqlens is not None:
+                self.cached_compressed_cu_seqlens2 = cu_seqlens.clone()
+            self.compress_k2_cache_varlen = key_states
+            split_sizes = (cu_seqlens[1:] - cu_seqlens[:-1]).tolist()
+            self.compress_k2_cache = list(torch.split(key_states, split_sizes))
+        else:
+            for index, k in enumerate(key_states):
+                if k is not None:
+                    self.compress_k2_cache[index] = torch.cat([self.compress_k2_cache[index], k], dim=0)
+            new_seq_lens = torch.tensor([tensor.shape[0] for tensor in self.compress_k2_cache], dtype=torch.int32)
+            new_cumsum = torch.cumsum(new_seq_lens, dim=0, dtype=torch.int32)
+            
+            self.compress_k2_cache_varlen = torch.cat(self.compress_k2_cache, dim=0)
+            self.cached_compressed_cu_seqlens2 = torch.cat([torch.tensor([0], dtype=torch.int32), new_cumsum]).to(self.compress_k2_cache_varlen.device)
+        return self.compress_k2_cache_varlen, self.cached_compressed_cu_seqlens2
+
+    def update_no_compress_k2(self, key_states, kernel_size=128, kernel_stride=64):
+        k_chunk_list = []
+        for index, k in enumerate(key_states):
+            if len(self.no_compress_k2_cache) <= index:
+                self.no_compress_k2_cache.append(k)
+            else:
+                self.no_compress_k2_cache[index] = torch.cat([self.no_compress_k2_cache[index], k], dim=0)
+                current_len = self.no_compress_k2_cache[index].shape[0]
+                if current_len >= kernel_size:
+                    k_chunk_list.append(self.no_compress_k2_cache[index][:kernel_size])
+                    self.no_compress_k2_cache[index] = self.no_compress_k2_cache[index][kernel_stride:]
+                else:
+                    k_chunk_list.append(None)
+        return k_chunk_list
+
+class InfLLMv2Cache(DynamicCache):
+    def __init__(self, config,num_hidden_layers: Optional[int] = None) -> None:
+        super().__init__(config=config)
+        self.layers = [InfLLMv2CacheLayer() for _ in range(num_hidden_layers)] if num_hidden_layers else []
+        self._seen_tokens = 0
+        
 
-        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
+    def update(self, key_states, value_states, layer_idx, cache_kwargs=None):
         if layer_idx == 0:
             self._seen_tokens += key_states.shape[-2]
+        return self.layers[layer_idx].update(key_states, value_states, cache_kwargs)
 
-        # 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
+    def update_no_rope_key(self, key_states, layer_idx, cache_kwargs=None):
+        return self.layers[layer_idx].update_no_rope_key(key_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.
-        """
+    def update_compress_k(self, key_states, layer_idx, cu_seqlens=None, cache_kwargs=None):
+        return self.layers[layer_idx].update_compress_k(key_states, cu_seqlens)
 
-        # Update the cache
-        if len(self.compress_k_cache) <= layer_idx:
-            self.compress_k_cache.append(key_states)
+    def update_no_compress_k(self, key_states, layer_idx, kernel_size=32, kernel_stride=16, cache_kwargs=None):
+        return self.layers[layer_idx].update_no_compress_k(key_states, kernel_size, kernel_stride)
 
-        # 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_compress_k2(self, key_states, layer_idx, cu_seqlens=None, cache_kwargs=None):
+        return self.layers[layer_idx].update_compress_k2(key_states, cu_seqlens)
 
-    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`.
+    def update_no_compress_k2(self, key_states, layer_idx, kernel_size=128, kernel_stride=64, cache_kwargs=None):
+        return self.layers[layer_idx].update_no_compress_k2(key_states, kernel_size, kernel_stride)
 
-        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)
+    def crop(self, max_length):
+        for layer in self.layers:
+            layer.crop(max_length)
 
-        current_len = self.no_compress_k_cache[layer_idx].shape[0]
+    def batch_repeat_interleave(self, repeats):
+        for layer in self.layers:
+            layer.batch_repeat_interleave(repeats)
 
-        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, ...]
+    def batch_select_indices(self, indices):
+        for layer in self.layers:
+            layer.batch_select_indices(indices)
 
 
 # This makes `_prepare_4d_causal_attention_mask` a leaf function in the FX graph.
@@ -661,22 +388,6 @@ 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
@@ -863,12 +574,9 @@ class MiniCPMMLP(nn.Module):
         self.config = config
         self.hidden_size = config.hidden_size
         self.intermediate_size = config.intermediate_size
-        self.gate_proj = LinearQuantizer(self.hidden_size, self.intermediate_size, bias=False, quant_type="ternary", bit=4, group_size=-1)
-        self.up_proj = LinearQuantizer(self.hidden_size, self.intermediate_size, bias=False, quant_type="ternary", bit=4, group_size=-1)
-        self.down_proj = LinearQuantizer(self.intermediate_size, self.hidden_size, bias=False, quant_type="ternary", bit=4, group_size=-1)
-        # self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
-        # self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
-        # self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
         self.act_fn = ACT2FN[config.hidden_act]
 
     def forward(self, x):
@@ -893,7 +601,21 @@ 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:
     """
     This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
@@ -936,14 +658,10 @@ class MiniCPMAttention(nn.Module):
                 f' and `num_heads`: {self.num_heads}).'
             )
 
-        # self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=config.attention_bias)
-        # self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=config.attention_bias)
-        # self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=config.attention_bias)
-        # self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=config.attention_bias)
-        self.q_proj = LinearQuantizer(config.hidden_size, config.num_attention_heads * self.head_dim, bias=config.attention_bias, quant_type="ternary", bit=4, group_size=-1)
-        self.k_proj = LinearQuantizer(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias, quant_type="ternary", bit=4, group_size=-1)
-        self.v_proj = LinearQuantizer(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias, quant_type="ternary", bit=4, group_size=-1)
-        self.o_proj = LinearQuantizer(config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.attention_bias, quant_type="ternary", bit=4, group_size=-1)
+        self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=config.attention_bias)
+        self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=config.attention_bias)
+        self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=config.attention_bias)
+        self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=config.attention_bias)
         self._init_rope()
 
     def _init_rope(self):
@@ -1028,15 +746,7 @@ 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)
@@ -1138,9 +848,7 @@ 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)
 
@@ -1312,9 +1020,11 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
         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.topk = self.config.sparse_config.get('topk', 64) + (self.window_size//self.block_size)
         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)
+        self.compress_k2 = CompressK(self.num_key_value_heads, self.head_dim, kernel_size=self.kernel_size*4, kernel_stride=self.kernel_stride*4)
 
     def forward(
         self,
@@ -1338,7 +1048,7 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
         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)
@@ -1356,9 +1066,7 @@ class MiniCPMInfLLMv2Attention(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)
 
@@ -1372,12 +1080,12 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
         key_states = key_states.transpose(1, 2)
         value_states = value_states.transpose(1, 2)
         if self.use_nope:
+            key_states_no_rope =past_key_value.update_no_rope_key(key_states_no_rope, self.layer_idx)
             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
 
@@ -1409,15 +1117,11 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
         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(
+        else:
+            attn_output = self._sparse_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)
 
@@ -1426,123 +1130,180 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
 
         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')
+    def _sparse_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]
+                # assert batch_size == 1, 'Only batch_size=1 is supported at the moment.'
+                if past_key_value!=None:
+                    compressed_k, compressed_cu_seqlens, compressed_k2, compressed_cu_seqlens2 = self.get_compress_k(
+                        key_states=key_states if self.use_nope ==False else no_rope_param['key_states_no_rope'],  # This can be optimized a bit;
+                        attention_mask=attention_mask,
+                        past_key_value=past_key_value,
+                        
+                    )
+
+                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
+                if no_rope_param != None:
+                    if max_seqlen_in_batch_q == 1:
+                        no_rope_param['query_states_no_rope'] = no_rope_param['query_states_no_rope'].squeeze(1)
+                    else:
+                        no_rope_param['query_states_no_rope'],_, _, _ = _unpad_one_tensor(no_rope_param['query_states_no_rope'],attention_mask=attention_mask)
+                if past_key_value==None:
+                    # compress_k use varlen form
+                    compressed_k, compressed_cu_seqlens = self.compress_k(key_states,cu_seqlens_k)
+                    compressed_k2, compressed_cu_seqlens2 = self.compress_k2(key_states,cu_seqlens_k)
+                else:
+                    # compressed_k and compressed_k2 already retrieved from get_compress_k above
+                    pass
+
+                
+                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,
+                    compressed_k=compressed_k, compressed_cu_seqlens=compressed_cu_seqlens,
+                    compressed_k2=compressed_k2, compressed_cu_seqlens2=compressed_cu_seqlens2
+                )
 
-        return attn_output
+                attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
+                
+            else:
+                raise ValueError('Need attention mask')
 
-    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
-    ):
+            return attn_output
+    def get_compress_k(self, key_states, attention_mask, past_key_value):
         """
-        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.
-
+        Get compressed key states and corresponding cumulative sequence lengths.
+        
         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)
+            key_states: Key states tensor
+            cu_seqlens_k: Cumulative sequence lengths for keys
+            past_key_value: Past key-value cache
+            no_rope_param: Optional parameter containing key states without rope
+            
+        Returns:
+            Tuple of (compressed_k, compressed_cu_seqlens, compressed_k2, compressed_cu_seqlens2)
         """
-        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)
+        
+        # Check if this is prefilling or initial compression condition
 
-            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)
+        is_prefilling = (
+            key_states.shape[1] >= self.dense_len and
+            (
+                not past_key_value.layers[self.layer_idx].compress_k_cache
+            )
+        )
+        
+        if is_prefilling:
+            unpadded_key_states, indices, cu_seqlens, max_seqlen_in_batch = _unpad_one_tensor(key_states,attention_mask=attention_mask)
+            # Compress the keys
+            compressed_k, compressed_cu_seqlens = self.compress_k(unpadded_key_states, cu_seqlens)
+            compressed_k2, compressed_cu_seqlens2 = self.compress_k2(unpadded_key_states, cu_seqlens)
+            
+            past_key_value.update_compress_k(
+                compressed_k, self.layer_idx, compressed_cu_seqlens)
+            past_key_value.update_compress_k2(
+                compressed_k2, self.layer_idx, compressed_cu_seqlens2)
+            
+            no_compress_k_list = []
+            # Compute and update no_compress_k
+            for i in range(len(compressed_cu_seqlens)-1):
+                no_compress_k_start = (compressed_cu_seqlens[i+1]- compressed_cu_seqlens[i]) * self.kernel_stride
+                
+                no_compress_k_list.append(unpadded_key_states[cu_seqlens[i]+no_compress_k_start:cu_seqlens[i+1]].clone())
 
-            # attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
+            past_key_value.update_no_compress_k(
+                no_compress_k_list, self.layer_idx,kernel_stride=self.kernel_stride, 
+                kernel_size=self.kernel_size)
+            
+            # Also update no_compress_k2
+            no_compress_k2_list = []
+            for i in range(len(compressed_cu_seqlens2)-1):
+                no_compress_k2_start = (compressed_cu_seqlens2[i+1]- compressed_cu_seqlens2[i]) * self.kernel_stride * 4
+                
+                no_compress_k2_list.append(unpadded_key_states[cu_seqlens[i]+no_compress_k2_start:cu_seqlens[i+1]].clone())
+
+            past_key_value.update_no_compress_k2(
+                no_compress_k2_list, self.layer_idx,kernel_stride=self.kernel_stride*4, 
+                kernel_size=self.kernel_size*4)
+                
         else:
-            raise ValueError('need attention mask')
-
-        return attn_output
-
+            # Decode case: incremental update
+            batch_size = key_states.shape[0] # key_states.shape = [batch_size, seq, k_head_num, head_dim]
+            key_states_split = list(torch.split(
+                key_states[:,-1:].squeeze(1), #[batch_size, seq, k_head_num, head_dim]->[batch_size, 1, k_head_num, head_dim]-> [batch_size, k_head_num, head_dim]
+                [1] * batch_size,dim=0,
+            ))
+            # Try to update no_compress_k buffer
+            no_compress_k_list = past_key_value.update_no_compress_k(
+                key_states_split, self.layer_idx, 
+                kernel_stride=self.kernel_stride, 
+                kernel_size=self.kernel_size)
+            new_compressed_k_list = []
+            for no_compress_k in no_compress_k_list:
+
+                if no_compress_k is not None:
+                    # We have enough tokens to compress
+                    new_compressed_k = no_compress_k.mean(dim=0, keepdim=True)  # [1, n_heads_k, head_dim]
+                    
+                    new_compressed_k_list.append(new_compressed_k)
+                else:
+                    new_compressed_k_list.append(None)
+            compressed_k, compressed_cu_seqlens = past_key_value.update_compress_k(new_compressed_k_list, self.layer_idx,)
+            
+            # For compress_k2, update no_compress_k2 buffer and compress when ready
+            no_compress_k2_list = past_key_value.update_no_compress_k2(
+                key_states_split, self.layer_idx, 
+                kernel_stride=self.kernel_stride*4, 
+                kernel_size=self.kernel_size*4)
+            new_compressed_k2_list = []
+            for no_compress_k2 in no_compress_k2_list:
+                if no_compress_k2 is not None:
+                    # We have enough tokens to compress for k2
+                    new_compressed_k2 = no_compress_k2.mean(dim=0, keepdim=True)  # [1, n_heads_k, head_dim]
+                    new_compressed_k2_list.append(new_compressed_k2)
+                else:
+                    new_compressed_k2_list.append(None)
+            compressed_k2, compressed_cu_seqlens2 = past_key_value.update_compress_k2(new_compressed_k2_list, self.layer_idx,)
+        
+        return compressed_k, compressed_cu_seqlens, compressed_k2, compressed_cu_seqlens2
     def sparse_forward(self,
                        query_layer,
                        key_layer,
@@ -1552,37 +1313,32 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
                        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_k=None, compressed_cu_seqlens=None,
+                       compressed_k2=None, compressed_cu_seqlens2=None):
         compressed_seqlens = compressed_cu_seqlens[1:] - compressed_cu_seqlens[:-1]
+        cache_lens = None
+        if max_seqlen_in_batch_q==1 and max_seqlen_in_batch_k>1: #decoding
+            seq_lens_k =  cu_seqlens_k[1:] - cu_seqlens_k[:-1]
+            cache_lens = seq_lens_k-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,
+            compressed_k2,
             self.kernel_size,
             self.kernel_stride,
             self.block_size,
             self.topk,
             cu_seqlens_q,
             compressed_cu_seqlens,
+            compressed_cu_seqlens2,
             max_seqlen_in_batch_q,
             compressed_seqlens.max().item(),
             None,
             init_blocks=self.init_blocks,
             local_blocks=self.local_blocks,
+            cache_lens=cache_lens
         )
-
         topk_attn_output = infllmv2_attn_varlen_func(
             query_layer,
             key_layer,
@@ -1594,102 +1350,14 @@ class MiniCPMInfLLMv2Attention(MiniCPMAttention):
             dropout_p=0.0,
             deterministic=False,
             softmax_scale=None,
-            causal=True,
+            causal=max_seqlen_in_batch_q != 1,
             return_attn_probs=False,
-            block_window_size=self.window_size // self.block_size,
+            # 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
     ):
@@ -1828,9 +1496,7 @@ 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)
@@ -2153,11 +1819,13 @@ 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)
+            # Calculate the usable length of past key values
+            past_key_values_length = past_key_values.get_seq_length() if isinstance(past_key_values, InfLLMv2Cache) else 0
+
+            # Initialize InfLLMv2Cache if needed
             if self.config.sparse_config is not None and torch.cuda.is_available() and past_key_values_length == 0:
-                past_key_values = DynamicCacheQKV()
+                past_key_values = InfLLMv2Cache(config = self.config, num_hidden_layers=self.config.num_hidden_layers)
 
         if position_ids is None:
             device = input_ids.device if input_ids is not None else inputs_embeds.device
@@ -2383,12 +2051,17 @@ 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]
+
+                if self.config.sparse_config is not None and torch.cuda.is_available() and cache_length == 0:
+                    past_key_values = InfLLMv2Cache(config = self.config, num_hidden_layers=self.config.num_hidden_layers)
+                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
@@ -2607,4 +2280,4 @@ class MiniCPMForSequenceClassification(MiniCPMPreTrainedModel):
             past_key_values=transformer_outputs.past_key_values,
             hidden_states=transformer_outputs.hidden_states,
             attentions=transformer_outputs.attentions,
-        )
+        )