[cherry-pick][Feature] Support vae tiling parallel encode (#2368) (#2538)

Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: David Chen <530634352@qq.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
authored and GitHub committed 2026-04-07 11:16:44 +08:00
1 parent 9b23589c80
commit 2f289c78db
7 files changed
+614 -35

No files matched your search

@@ -93,7 +93,7 @@ class DistributedAutoencoderKL_base(DistributedVaeMixin):
_, _, latent_h, latent_w = z.shape
scale = int(2 ** (len(self.config.block_out_channels) - 1))
max_parallel_size = self.distributed_decoder.parallel_size
max_parallel_size = self.distributed_executor.parallel_size
root = int(math.sqrt(max_parallel_size))
for rows in range(root, 0, -1):
@@ -187,7 +187,7 @@ class DistributedAutoencoderKL_base(DistributedVaeMixin):
if split is not None:
strategy = "tile" if split == self.tile_split else "patch"
logger.info(f"Decode run with distributed executor, split strategy is {strategy}")
result = self.distributed_decoder.execute(
result = self.distributed_executor.execute(
z, DistributedOperator(split=split, exec=exec, merge=merge), broadcast_result=False
)
if not return_dict: