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

Signed-off-by: dengyunyang <584797741@qq.com>
This commit is contained in:
dengyunyang authored and GitHub committed 2026-03-03 15:48:51 +08:00
1 parent e7f2c88701
commit d275c0c993
18 files changed
+1336 -60

No files matched your search

@@ -13,9 +13,6 @@ import numpy as np
import torch
import torch.distributed
from diffusers.image_processor import VaeImageProcessor
from diffusers.models.autoencoders.autoencoder_kl_qwenimage import (
AutoencoderKLQwenImage,
)
from diffusers.schedulers.scheduling_flow_match_euler_discrete import (
FlowMatchEulerDiscreteScheduler,
)
@@ -25,6 +22,7 @@ from transformers import Qwen2_5_VLForConditionalGeneration, Qwen2Tokenizer
from vllm.model_executor.models.utils import AutoWeightsLoader
from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
from vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_qwenimage import DistributedAutoencoderKLQwenImage
from vllm_omni.diffusion.distributed.utils import get_local_device
from vllm_omni.diffusion.model_loader.diffusers_loader import DiffusersPipelineLoader
from vllm_omni.diffusion.models.qwen_image.cfg_parallel import (
@@ -269,9 +267,9 @@ class QwenImagePipeline(nn.Module, QwenImageCFGParallelMixin):
self.text_encoder = Qwen2_5_VLForConditionalGeneration.from_pretrained(
model, subfolder="text_encoder", local_files_only=local_files_only
)
self.vae = AutoencoderKLQwenImage.from_pretrained(model, subfolder="vae", local_files_only=local_files_only).to(
self.device
)
self.vae = DistributedAutoencoderKLQwenImage.from_pretrained(
model, subfolder="vae", local_files_only=local_files_only
).to(self.device)
transformer_kwargs = get_transformer_config_kwargs(od_config.tf_model_config, QwenImageTransformer2DModel)
quant_config = get_vllm_quant_config_for_layers(od_config.quantization_config)
self.transformer = QwenImageTransformer2DModel(