cache-dit 0.3.2__py3-none-any.whl → 1.0.14__py3-none-any.whl

cache_dit-1.0.14.dist-info/licenses/LICENSE

@@ -0,0 +1,203 @@
+Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cache_dit/cache_factory/__init__.py

@@ -1,28 +0,0 @@
-from cache_dit.cache_factory.cache_types import CacheType
-from cache_dit.cache_factory.cache_types import cache_type
-from cache_dit.cache_factory.cache_types import block_range
-
-from cache_dit.cache_factory.forward_pattern import ForwardPattern
-from cache_dit.cache_factory.params_modifier import ParamsModifier
-from cache_dit.cache_factory.patch_functors import PatchFunctor
-
-from cache_dit.cache_factory.block_adapters import BlockAdapter
-from cache_dit.cache_factory.block_adapters import BlockAdapterRegistry
-
-from cache_dit.cache_factory.cache_contexts import CachedContext
-from cache_dit.cache_factory.cache_contexts import BasicCacheConfig
-from cache_dit.cache_factory.cache_contexts import CachedContextManager
-from cache_dit.cache_factory.cache_contexts import CalibratorConfig
-from cache_dit.cache_factory.cache_contexts import TaylorSeerCalibratorConfig
-from cache_dit.cache_factory.cache_contexts import FoCaCalibratorConfig
-
-from cache_dit.cache_factory.cache_blocks import CachedBlocks
-
-from cache_dit.cache_factory.cache_adapters import CachedAdapter
-
-from cache_dit.cache_factory.cache_interface import enable_cache
-from cache_dit.cache_factory.cache_interface import disable_cache
-from cache_dit.cache_factory.cache_interface import supported_pipelines
-from cache_dit.cache_factory.cache_interface import get_adapter
-
-from cache_dit.cache_factory.utils import load_options

cache_dit/cache_factory/block_adapters/block_registers.py

@@ -1,90 +0,0 @@
-from typing import Any, Tuple, List, Dict, Callable
-
-from diffusers import DiffusionPipeline
-from cache_dit.cache_factory.block_adapters.block_adapters import BlockAdapter
-
-from cache_dit.logger import init_logger
-
-logger = init_logger(__name__)
-
-
-class BlockAdapterRegistry:
-    _adapters: Dict[str, Callable[..., BlockAdapter]] = {}
-    _predefined_adapters_has_separate_cfg: List[str] = [
-        "QwenImage",
-        "Wan",
-        "CogView4",
-        "Cosmos",
-        "SkyReelsV2",
-        "Chroma",
-        "Lumina2",
-    ]
-
-    @classmethod
-    def register(cls, name: str, supported: bool = True):
-        def decorator(
-            func: Callable[..., BlockAdapter]
-        ) -> Callable[..., BlockAdapter]:
-            if supported:
-                cls._adapters[name] = func
-            return func
-
-        return decorator
-
-    @classmethod
-    def get_adapter(
-        cls,
-        pipe: DiffusionPipeline | str | Any,
-        **kwargs,
-    ) -> BlockAdapter:
-        if not isinstance(pipe, str):
-            pipe_cls_name: str = pipe.__class__.__name__
-        else:
-            pipe_cls_name = pipe
-
-        for name in cls._adapters:
-            if pipe_cls_name.startswith(name):
-                return cls._adapters[name](pipe, **kwargs)
-
-        return BlockAdapter()
-
-    @classmethod
-    def has_separate_cfg(
-        cls,
-        pipe_or_adapter: DiffusionPipeline | BlockAdapter | Any,
-    ) -> bool:
-
-        # Prefer custom setting from block adapter.
-        if isinstance(pipe_or_adapter, BlockAdapter):
-            return pipe_or_adapter.has_separate_cfg
-
-        has_separate_cfg = False
-        if isinstance(pipe_or_adapter, DiffusionPipeline):
-            has_separate_cfg = cls.get_adapter(
-                pipe_or_adapter,
-                skip_post_init=True,  # check cfg setting only
-            ).has_separate_cfg
-
-        if has_separate_cfg:
-            return True
-
-        pipe_cls_name = pipe_or_adapter.__class__.__name__
-        for name in cls._predefined_adapters_has_separate_cfg:
-            if pipe_cls_name.startswith(name):
-                return True
-
-        return False
-
-    @classmethod
-    def is_supported(cls, pipe) -> bool:
-        pipe_cls_name: str = pipe.__class__.__name__
-
-        for name in cls._adapters:
-            if pipe_cls_name.startswith(name):
-                return True
-        return False
-
-    @classmethod
-    def supported_pipelines(cls, **kwargs) -> Tuple[int, List[str]]:
-        val_pipelines = cls._adapters.keys()
-        return len(val_pipelines), [p + "*" for p in val_pipelines]

cache_dit/cache_factory/cache_adapters/__init__.py

@@ -1 +0,0 @@
-from cache_dit.cache_factory.cache_adapters.cache_adapter import CachedAdapter

cache_dit/cache_factory/cache_blocks/__init__.py

@@ -1,72 +0,0 @@
-import torch
-
-from cache_dit.cache_factory import ForwardPattern
-from cache_dit.cache_factory.cache_contexts.cache_context import CachedContext
-from cache_dit.cache_factory.cache_contexts.cache_manager import (
-    CachedContextManager,
-)
-
-from cache_dit.cache_factory.cache_blocks.pattern_0_1_2 import (
-    CachedBlocks_Pattern_0_1_2,
-)
-from cache_dit.cache_factory.cache_blocks.pattern_3_4_5 import (
-    CachedBlocks_Pattern_3_4_5,
-)
-
-from cache_dit.logger import init_logger
-
-logger = init_logger(__name__)
-
-
-class CachedBlocks:
-    def __new__(
-        cls,
-        # 0. Transformer blocks configuration
-        transformer_blocks: torch.nn.ModuleList,
-        transformer: torch.nn.Module = None,
-        forward_pattern: ForwardPattern = None,
-        check_forward_pattern: bool = True,
-        check_num_outputs: bool = True,
-        # 1. Cache context configuration
-        # 'transformer_blocks', 'blocks', 'single_transformer_blocks',
-        # 'layers', 'single_stream_blocks', 'double_stream_blocks'
-        cache_prefix: str = None,  # cache_prefix maybe un-need.
-        # Usually, blocks_name, etc.
-        cache_context: CachedContext | str = None,
-        cache_manager: CachedContextManager = None,
-        **kwargs,
-    ):
-        assert transformer is not None, "transformer can't be None."
-        assert forward_pattern is not None, "forward_pattern can't be None."
-        assert cache_context is not None, "cache_context can't be None."
-        assert cache_manager is not None, "cache_manager can't be None."
-        if forward_pattern in CachedBlocks_Pattern_0_1_2._supported_patterns:
-            return CachedBlocks_Pattern_0_1_2(
-                # 0. Transformer blocks configuration
-                transformer_blocks,
-                transformer=transformer,
-                forward_pattern=forward_pattern,
-                check_forward_pattern=check_forward_pattern,
-                check_num_outputs=check_num_outputs,
-                # 1. Cache context configuration
-                cache_prefix=cache_prefix,
-                cache_context=cache_context,
-                cache_manager=cache_manager,
-                **kwargs,
-            )
-        elif forward_pattern in CachedBlocks_Pattern_3_4_5._supported_patterns:
-            return CachedBlocks_Pattern_3_4_5(
-                # 0. Transformer blocks configuration
-                transformer_blocks,
-                transformer=transformer,
-                forward_pattern=forward_pattern,
-                check_forward_pattern=check_forward_pattern,
-                check_num_outputs=check_num_outputs,
-                # 1. Cache context configuration
-                cache_prefix=cache_prefix,
-                cache_context=cache_context,
-                cache_manager=cache_manager,
-                **kwargs,
-            )
-        else:
-            raise ValueError(f"Pattern {forward_pattern} is not supported now!")

cache_dit/cache_factory/cache_blocks/pattern_0_1_2.py

@@ -1,16 +0,0 @@
-from cache_dit.cache_factory import ForwardPattern
-from cache_dit.cache_factory.cache_blocks.pattern_base import (
-    CachedBlocks_Pattern_Base,
-)
-from cache_dit.logger import init_logger
-
-logger = init_logger(__name__)
-
-
-class CachedBlocks_Pattern_0_1_2(CachedBlocks_Pattern_Base):
-    _supported_patterns = [
-        ForwardPattern.Pattern_0,
-        ForwardPattern.Pattern_1,
-        ForwardPattern.Pattern_2,
-    ]
-    ...

cache_dit/cache_factory/cache_blocks/pattern_3_4_5.py

@@ -1,238 +0,0 @@
-import torch
-
-from cache_dit.cache_factory import ForwardPattern
-from cache_dit.cache_factory.cache_blocks.pattern_base import (
-    CachedBlocks_Pattern_Base,
-)
-from cache_dit.logger import init_logger
-
-logger = init_logger(__name__)
-
-
-class CachedBlocks_Pattern_3_4_5(CachedBlocks_Pattern_Base):
-    _supported_patterns = [
-        ForwardPattern.Pattern_3,
-        ForwardPattern.Pattern_4,
-        ForwardPattern.Pattern_5,
-    ]
-
-    def forward(
-        self,
-        hidden_states: torch.Tensor,
-        *args,
-        **kwargs,
-    ):
-        # Use it's own cache context.
-        self.cache_manager.set_context(self.cache_context)
-        self._check_cache_params()
-
-        original_hidden_states = hidden_states
-        # Call first `n` blocks to process the hidden states for
-        # more stable diff calculation.
-        hidden_states, new_encoder_hidden_states = self.call_Fn_blocks(
-            hidden_states,
-            *args,
-            **kwargs,
-        )
-
-        Fn_hidden_states_residual = hidden_states - original_hidden_states
-        del original_hidden_states
-
-        self.cache_manager.mark_step_begin()
-        # Residual L1 diff or Hidden States L1 diff
-        can_use_cache = self.cache_manager.can_cache(
-            (
-                Fn_hidden_states_residual
-                if not self.cache_manager.is_l1_diff_enabled()
-                else hidden_states
-            ),
-            parallelized=self._is_parallelized(),
-            prefix=(
-                f"{self.cache_prefix}_Fn_residual"
-                if not self.cache_manager.is_l1_diff_enabled()
-                else f"{self.cache_prefix}_Fn_hidden_states"
-            ),
-        )
-
-        torch._dynamo.graph_break()
-        if can_use_cache:
-            self.cache_manager.add_cached_step()
-            del Fn_hidden_states_residual
-            hidden_states, new_encoder_hidden_states = (
-                self.cache_manager.apply_cache(
-                    hidden_states,
-                    new_encoder_hidden_states,  # encoder_hidden_states not use cache
-                    prefix=(
-                        f"{self.cache_prefix}_Bn_residual"
-                        if self.cache_manager.is_cache_residual()
-                        else f"{self.cache_prefix}_Bn_hidden_states"
-                    ),
-                    encoder_prefix=(
-                        f"{self.cache_prefix}_Bn_residual"
-                        if self.cache_manager.is_encoder_cache_residual()
-                        else f"{self.cache_prefix}_Bn_hidden_states"
-                    ),
-                )
-            )
-            torch._dynamo.graph_break()
-            # Call last `n` blocks to further process the hidden states
-            # for higher precision.
-            if self.cache_manager.Bn_compute_blocks() > 0:
-                hidden_states, new_encoder_hidden_states = self.call_Bn_blocks(
-                    hidden_states,
-                    *args,
-                    **kwargs,
-                )
-        else:
-            self.cache_manager.set_Fn_buffer(
-                Fn_hidden_states_residual,
-                prefix=f"{self.cache_prefix}_Fn_residual",
-            )
-            if self.cache_manager.is_l1_diff_enabled():
-                # for hidden states L1 diff
-                self.cache_manager.set_Fn_buffer(
-                    hidden_states,
-                    f"{self.cache_prefix}_Fn_hidden_states",
-                )
-            del Fn_hidden_states_residual
-            torch._dynamo.graph_break()
-            old_encoder_hidden_states = new_encoder_hidden_states
-            (
-                hidden_states,
-                new_encoder_hidden_states,
-                hidden_states_residual,
-            ) = self.call_Mn_blocks(  # middle
-                hidden_states,
-                *args,
-                **kwargs,
-            )
-
-            torch._dynamo.graph_break()
-            if self.cache_manager.is_cache_residual():
-                self.cache_manager.set_Bn_buffer(
-                    hidden_states_residual,
-                    prefix=f"{self.cache_prefix}_Bn_residual",
-                )
-            else:
-                self.cache_manager.set_Bn_buffer(
-                    hidden_states,
-                    prefix=f"{self.cache_prefix}_Bn_hidden_states",
-                )
-
-            if new_encoder_hidden_states is not None:
-                new_encoder_hidden_states_residual = (
-                    new_encoder_hidden_states - old_encoder_hidden_states
-                )
-            if self.cache_manager.is_encoder_cache_residual():
-                if new_encoder_hidden_states is not None:
-                    self.cache_manager.set_Bn_encoder_buffer(
-                        new_encoder_hidden_states_residual,
-                        prefix=f"{self.cache_prefix}_Bn_residual",
-                    )
-            else:
-                if new_encoder_hidden_states is not None:
-                    self.cache_manager.set_Bn_encoder_buffer(
-                        new_encoder_hidden_states_residual,
-                        prefix=f"{self.cache_prefix}_Bn_hidden_states",
-                    )
-            torch._dynamo.graph_break()
-            # Call last `n` blocks to further process the hidden states
-            # for higher precision.
-            if self.cache_manager.Bn_compute_blocks() > 0:
-                hidden_states, new_encoder_hidden_states = self.call_Bn_blocks(
-                    hidden_states,
-                    *args,
-                    **kwargs,
-                )
-
-        torch._dynamo.graph_break()
-
-        return (
-            hidden_states
-            if self.forward_pattern.Return_H_Only
-            else (
-                (hidden_states, new_encoder_hidden_states)
-                if self.forward_pattern.Return_H_First
-                else (new_encoder_hidden_states, hidden_states)
-            )
-        )
-
-    def call_Fn_blocks(
-        self,
-        hidden_states: torch.Tensor,
-        *args,
-        **kwargs,
-    ):
-        new_encoder_hidden_states = None
-        for block in self._Fn_blocks():
-            hidden_states = block(
-                hidden_states,
-                *args,
-                **kwargs,
-            )
-            if not isinstance(hidden_states, torch.Tensor):  # Pattern 4, 5
-                hidden_states, new_encoder_hidden_states = hidden_states
-                if not self.forward_pattern.Return_H_First:
-                    hidden_states, new_encoder_hidden_states = (
-                        new_encoder_hidden_states,
-                        hidden_states,
-                    )
-
-        return hidden_states, new_encoder_hidden_states
-
-    def call_Mn_blocks(
-        self,
-        hidden_states: torch.Tensor,
-        *args,
-        **kwargs,
-    ):
-        original_hidden_states = hidden_states
-        new_encoder_hidden_states = None
-        for block in self._Mn_blocks():
-            hidden_states = block(
-                hidden_states,
-                *args,
-                **kwargs,
-            )
-            if not isinstance(hidden_states, torch.Tensor):  # Pattern 4, 5
-                hidden_states, new_encoder_hidden_states = hidden_states
-                if not self.forward_pattern.Return_H_First:
-                    hidden_states, new_encoder_hidden_states = (
-                        new_encoder_hidden_states,
-                        hidden_states,
-                    )
-        # compute hidden_states residual
-        hidden_states = hidden_states.contiguous()
-        hidden_states_residual = hidden_states - original_hidden_states
-
-        return (
-            hidden_states,
-            new_encoder_hidden_states,
-            hidden_states_residual,
-        )
-
-    def call_Bn_blocks(
-        self,
-        hidden_states: torch.Tensor,
-        *args,
-        **kwargs,
-    ):
-        new_encoder_hidden_states = None
-        if self.cache_manager.Bn_compute_blocks() == 0:
-            return hidden_states, new_encoder_hidden_states
-
-        for block in self._Bn_blocks():
-            hidden_states = block(
-                hidden_states,
-                *args,
-                **kwargs,
-            )
-            if not isinstance(hidden_states, torch.Tensor):  # Pattern 4,5
-                hidden_states, new_encoder_hidden_states = hidden_states
-                if not self.forward_pattern.Return_H_First:
-                    hidden_states, new_encoder_hidden_states = (
-                        new_encoder_hidden_states,
-                        hidden_states,
-                    )
-
-        return hidden_states, new_encoder_hidden_states