[Feature] Spatially-sharded (SP) decode for the Wan VAE (#4620)

Signed-off-by: Rahul Steiger <rsteiger@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Rahul SteigerandHongsheng Liu authored and GitHub committed 2026-06-27 09:01:25 +08:00
1 parent 47871d5e20
commit 327e9dcaf2
17 files changed
+1416 -11

No files matched your search

@@ -5,11 +5,13 @@ from contextlib import nullcontext
from typing import Any
import torch
import torch.distributed as dist
from diffusers.models.autoencoders import AutoencoderKLWan
from diffusers.models.autoencoders.autoencoder_kl_wan import unpatchify
from diffusers.models.autoencoders.vae import DecoderOutput
from vllm.logger import init_logger
from vllm_omni.diffusion.distributed.autoencoders import wan_spatial_shard
from vllm_omni.diffusion.distributed.autoencoders.distributed_vae_executor import (
DistributedOperator,
DistributedVaeMixin,
@@ -268,10 +270,54 @@ class DistributedAutoencoderKLWan(OmniAutoencoderKLWan, DistributedVaeMixin):
dec = torch.clamp(dec, min=-1.0, max=1.0)
return dec
def _spatial_shard_decode_split_dim(self) -> str | None:
mode = self.distributed_executor.parallel_mode
if mode == "spatial_shard_width":
return "width"
if mode == "spatial_shard_height":
return "height"
return None
def _spatial_shard_decode_enabled(self, z: torch.Tensor) -> bool:
split_dim = self._spatial_shard_decode_split_dim()
if split_dim is None:
return False
if z.ndim != 5:
logger.warning("Wan VAE spatial sharded decode expects 5D latent input; falling back to tiled decode.")
return False
if not self.is_distributed_enabled():
return False
group = self.distributed_executor.group
world_size = dist.get_world_size(group=group)
requested_size = int(self.distributed_executor.parallel_size)
if requested_size != world_size:
logger.warning(
"Wan VAE spatial sharded decode currently requires vae_patch_parallel_size "
"to match the DIT group size; falling back to tiled decode. "
"requested=%s dit_group=%s split_dim=%s",
requested_size,
world_size,
split_dim,
)
return False
return True
def tiled_decode(self, z: torch.Tensor, return_dict: bool = True):
if not self.is_distributed_enabled():
return super().tiled_decode(z, return_dict=return_dict)
if self._spatial_shard_decode_enabled(z):
split_dim = self._spatial_shard_decode_split_dim()
logger.debug("Decode running with Wan VAE spatial_shard_%s mode", split_dim)
return wan_spatial_shard.spatial_shard_decode(
self,
z,
group=self.distributed_executor.group,
return_dict=return_dict,
split_dim=split_dim,
)
logger.debug("Decode running with distributed executor")
result = self.distributed_executor.execute(
z,