[Core] Add batch parallel VAE decode (#8162)

Signed-off-by: QianCyrus <101633534+QianCyrus@users.noreply.github.com>
This commit is contained in:
QianCyrus authored and GitHub committed 2026-10-06 13:51:35 +08:00
1 parent 2bcd1e449a
commit c2cd13c009
12 files changed
+460 -37

No files matched your search

+4 -3
View File
@@ -1003,8 +1003,8 @@ class OmniServeCommand(CLISubcommand):
"--vae-patch-parallel-size",
type=int,
default=1,
help="VAE Patch Parallelism degree for diffusion models. "
"Distributes VAE decode workload across multiple ranks by splitting the latent spatially. "
help="VAE parallelism degree for diffusion models. "
"Distributes VAE decode across ranks using --vae-parallel-mode. "
"Equivalent to setting DiffusionParallelConfig.vae_patch_parallel_size.",
)
omni_config_group.add_argument(
@@ -1019,9 +1019,10 @@ class OmniServeCommand(CLISubcommand):
"--vae-parallel-mode",
type=str,
default="tile",
choices=["tile", "spatial_shard_height", "spatial_shard_width"],
choices=["tile", "batch", "spatial_shard_height", "spatial_shard_width"],
help="VAE parallel decode strategy for diffusion models. "
"'tile' (default) uses patch/tile parallel decode; "
"'batch' distributes complete images for AutoencoderKL/Flux2 with DP/PP/CFG sizes of 1; "
"'spatial_shard_height'/'spatial_shard_width' use spatially-sharded decode that splits "
"decoder feature maps along height/width and exchanges halo regions. The "
"'spatial_shard_*' modes require vae_patch_parallel_size to match the DiT group size. "