remove qkv fusion

Author: a-r-r-o-w

src/diffusers/models/transformers/transformer_cogview3plus.py

@@ -24,7 +24,6 @@
     Attention,
     AttentionProcessor,
     CogVideoXAttnProcessor2_0,
-    FusedCogVideoXAttnProcessor2_0,
 )
 from ...models.modeling_utils import ModelMixin
 from ...models.normalization import AdaLayerNormContinuous
@@ -277,46 +276,6 @@ def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
         for name, module in self.named_children():
             fn_recursive_attn_processor(name, module, processor)
 
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.fuse_qkv_projections with FusedAttnProcessor2_0->FusedCogVideoXAttnProcessor2_0
-    def fuse_qkv_projections(self):
-        """
-        Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
-        are fused. For cross-attention modules, key and value projection matrices are fused.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-        """
-        self.original_attn_processors = None
-
-        for _, attn_processor in self.attn_processors.items():
-            if "Added" in str(attn_processor.__class__.__name__):
-                raise ValueError("`fuse_qkv_projections()` is not supported for models having added KV projections.")
-
-        self.original_attn_processors = self.attn_processors
-
-        for module in self.modules():
-            if isinstance(module, Attention):
-                module.fuse_projections(fuse=True)
-
-        self.set_attn_processor(FusedCogVideoXAttnProcessor2_0())
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.unfuse_qkv_projections
-    def unfuse_qkv_projections(self):
-        """Disables the fused QKV projection if enabled.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-
-        """
-        if self.original_attn_processors is not None:
-            self.set_attn_processor(self.original_attn_processors)
-
     def _set_gradient_checkpointing(self, module, value=False):
         if hasattr(module, "gradient_checkpointing"):
             module.gradient_checkpointing = value

src/diffusers/pipelines/cogview3/pipeline_cogview3plus.py

@@ -397,19 +397,6 @@ def check_inputs(
                     f" {negative_prompt_embeds.shape}."
                 )
 
-    def fuse_qkv_projections(self) -> None:
-        r"""Enables fused QKV projections."""
-        self.fusing_transformer = True
-        self.transformer.fuse_qkv_projections()
-
-    def unfuse_qkv_projections(self) -> None:
-        r"""Disable QKV projection fusion if enabled."""
-        if not self.fusing_transformer:
-            logger.warning("The Transformer was not initially fused for QKV projections. Doing nothing.")
-        else:
-            self.transformer.unfuse_qkv_projections()
-            self.fusing_transformer = False
-
     @property
     def guidance_scale(self):
         return self._guidance_scale