[FEATURE] Tile/Patch parallelism refactor for easily support other models (#1366)

Signed-off-by: dengyunyang <584797741@qq.com>

vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2.py

@@ -11,13 +11,13 @@ from typing import Any, cast
 
 import PIL.Image
 import torch
-from diffusers import AutoencoderKLWan
 from diffusers.utils.torch_utils import randn_tensor
 from torch import nn
 from transformers import AutoTokenizer, UMT5EncoderModel
 from vllm.model_executor.models.utils import AutoWeightsLoader
 
 from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
+from vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan import DistributedAutoencoderKLWan
 from vllm_omni.diffusion.distributed.cfg_parallel import CFGParallelMixin
 from vllm_omni.diffusion.distributed.utils import get_local_device
 from vllm_omni.diffusion.model_loader.diffusers_loader import DiffusersPipelineLoader
@@ -267,7 +267,7 @@ class Wan22Pipeline(nn.Module, CFGParallelMixin):
         self.text_encoder = UMT5EncoderModel.from_pretrained(
             model, subfolder="text_encoder", torch_dtype=dtype, local_files_only=local_files_only
         ).to(self.device)
-        self.vae = AutoencoderKLWan.from_pretrained(
+        self.vae = DistributedAutoencoderKLWan.from_pretrained(
             model, subfolder="vae", torch_dtype=torch.float32, local_files_only=local_files_only
         ).to(self.device)
 

vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2_i2v.py

@@ -11,13 +11,13 @@ from typing import Any, cast
 import numpy as np
 import PIL.Image
 import torch
-from diffusers import AutoencoderKLWan
 from diffusers.utils.torch_utils import randn_tensor
 from torch import nn
 from transformers import AutoTokenizer, CLIPImageProcessor, CLIPVisionModel, UMT5EncoderModel
 from vllm.model_executor.models.utils import AutoWeightsLoader
 
 from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
+from vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan import DistributedAutoencoderKLWan
 from vllm_omni.diffusion.distributed.cfg_parallel import CFGParallelMixin
 from vllm_omni.diffusion.distributed.utils import get_local_device
 from vllm_omni.diffusion.model_loader.diffusers_loader import DiffusersPipelineLoader
@@ -210,7 +210,7 @@ class Wan22I2VPipeline(nn.Module, SupportImageInput, CFGParallelMixin):
             self.image_encoder = None
 
         # VAE
-        self.vae = AutoencoderKLWan.from_pretrained(
+        self.vae = DistributedAutoencoderKLWan.from_pretrained(
             model, subfolder="vae", torch_dtype=torch.float32, local_files_only=local_files_only
         ).to(self.device)