[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

@@ -109,6 +109,12 @@ def parse_args() -> argparse.Namespace:
default=1,
help="Number of GPUs used for tensor parallelism (TP) inside the DiT.",
)
parser.add_argument(
"--vae-patch-parallel-size",
type=int,
default=1,
help="Number of GPUs used for VAE patch/tile parallelism (decode).",
)
return parser.parse_args()
@@ -141,6 +147,7 @@ def main():
ring_degree=args.ring_degree,
cfg_parallel_size=args.cfg_parallel_size,
tensor_parallel_size=args.tensor_parallel_size,
vae_patch_parallel_size=args.vae_patch_parallel_size,
)
# Check if profiling is requested via environment variable
@@ -172,7 +179,9 @@ def main():
print(f" Inference steps: {args.num_inference_steps}")
print(f" Frames: {args.num_frames}")
print(
f" Parallel configuration: ulysses_degree={args.ulysses_degree}, ring_degree={args.ring_degree}, cfg_parallel_size={args.cfg_parallel_size}, tensor_parallel_size={args.tensor_parallel_size}"
f" Parallel configuration: ulysses_degree={args.ulysses_degree}, ring_degree={args.ring_degree},"
f" cfg_parallel_size={args.cfg_parallel_size}, tensor_parallel_size={args.tensor_parallel_size},"
f" vae_patch_parallel_size={args.vae_patch_parallel_size}"
)
print(f" Video size: {args.width}x{args.height}")
print(f"{'=' * 60}\n")