fix(diffusion): address Wan auto decode review feedback

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu committed 2026-08-12 11:49:47 +08:00
1 parent 879d19c4c2
commit c8210b8b5c
7 files changed
+33 -71

No files matched your search

+4 -4
View File
@@ -210,11 +210,11 @@ class DiffusionParallelConfig:
vae_parallel_mode: str = "tile"
"""VAE parallel decode strategy.
- "tile": Patch/tile parallel decode (default). Each rank decodes a subset
of spatial tiles and the results are stitched on rank 0.
- "auto": Select the longer spatial-shard axis for validated Wan tiled
decodes on a full DiT-group topology; otherwise use patch/tile parallel
decode.
- "tile": Patch/tile parallel decode (default). Each rank decodes a subset
of spatial tiles and the results are stitched on rank 0.
- "spatial_shard_height": Spatially-sharded decode that splits decoder
feature maps along height and exchanges halo rows around spatial
convolutions.
@@ -254,9 +254,9 @@ class DiffusionParallelConfig:
assert self.allgather_degree > 0, "AllGather degree must be > 0"
assert self.cfg_parallel_size > 0, "CFG parallel size must be > 0"
assert self.vae_patch_parallel_size > 0, "VAE patch parallel size must be > 0"
assert self.vae_parallel_mode in {"auto", "tile", "spatial_shard_height", "spatial_shard_width"}, (
assert self.vae_parallel_mode in {"tile", "auto", "spatial_shard_height", "spatial_shard_width"}, (
"vae_parallel_mode must be one of "
"{'auto', 'tile', 'spatial_shard_height', 'spatial_shard_width'}, "
"{'tile', 'auto', 'spatial_shard_height', 'spatial_shard_width'}, "
f"but got {self.vae_parallel_mode!r}."
)
if self.allgather_degree > 1:
@@ -47,27 +47,6 @@ def select_auto_spatial_shard_split_dim(
return max(candidates, key=lambda candidate: (candidate[0], candidate[1] == "width"))[1]
def prepare_pipeline_wan_spatial_shard_decode(pipeline: torch.nn.Module) -> None:
"""Install eligible Wan wrappers while weight allocations are still tagged."""
from vllm_omni.diffusion.offloader.module_collector import ModuleDiscovery
if not dist.is_initialized():
return
for vae in ModuleDiscovery.discover(pipeline).vaes:
if not isinstance(vae, DistributedAutoencoderKLWan):
continue
executor = vae.distributed_executor
mode = executor.parallel_mode
if mode not in {"auto", "spatial_shard_height", "spatial_shard_width"}:
continue
requested_size = int(executor.parallel_size)
world_size = dist.get_world_size(group=executor.group)
if requested_size <= 1 or requested_size != world_size:
continue
split_dim = "width" if mode == "spatial_shard_width" else "height"
wan_spatial_shard.install_wan_spatial_shard_decode(vae, executor.group, split_dim=split_dim)
class OmniAutoencoderKLWan(AutoencoderKLWan):
def _execution_context(self):
try:
@@ -101,6 +80,19 @@ class DistributedAutoencoderKLWan(OmniAutoencoderKLWan, DistributedVaeMixin):
model.init_distributed()
return model
def set_parallel_size(self, parallel_size: int, mode: str = "tile") -> None:
super().set_parallel_size(parallel_size, mode=mode)
if mode not in {"auto", "spatial_shard_height", "spatial_shard_width"}:
return
executor = self.distributed_executor
world_size = dist.get_world_size(group=executor.group)
if parallel_size <= 1 or parallel_size != world_size:
return
split_dim = "width" if mode == "spatial_shard_width" else "height"
wan_spatial_shard.install_wan_spatial_shard_decode(self, executor.group, split_dim=split_dim)
def tile_split(self, z: torch.Tensor) -> tuple[list[TileTask], GridSpec]:
_, _, num_frames, height, width = z.shape
sample_height = height * self.spatial_compression_ratio
@@ -32,9 +32,6 @@ from vllm_omni.diffusion.compile import regionally_compile
from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
from vllm_omni.diffusion.diffusion_kv.metadata import DiffusionKVMetadata
from vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan import (
prepare_pipeline_wan_spatial_shard_decode,
)
from vllm_omni.diffusion.forward_context import set_forward_context
from vllm_omni.diffusion.model_loader.diffusers_loader import DiffusersPipelineLoader
from vllm_omni.diffusion.models.interface import (
@@ -269,7 +266,6 @@ class DiffusionModelRunner(OmniConnectorModelRunnerMixin):
custom_pipeline_name=custom_pipeline_name,
device=self.device,
)
prepare_pipeline_wan_spatial_shard_decode(self.pipeline)
time_after_load = time.perf_counter()
logger.info(