[diffusion] add tp support for qwen-image and refactor some tests (#830)

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
This commit is contained in:
Jiangyun Zhu authored and GitHub committed 2026-01-19 14:20:31 +08:00
1 parent 5e7035e183
commit 3fc4f988ea
6 files changed
+228 -150

No files matched your search

@@ -181,6 +181,12 @@ def parse_args() -> argparse.Namespace:
default=1,
help="Number of GPUs used for ring sequence parallelism.",
)
parser.add_argument(
"--tensor_parallel_size",
type=int,
default=1,
help="Number of GPUs used for tensor parallelism (TP) inside the DiT.",
)
parser.add_argument("--layers", type=int, default=4, help="Number of layers to decompose the input image into.")
parser.add_argument(
"--resolution",
@@ -301,7 +307,10 @@ def main():
vae_use_slicing = is_npu()
vae_use_tiling = is_npu()
parallel_config = DiffusionParallelConfig(
ulysses_degree=args.ulysses_degree, ring_degree=args.ring_degree, cfg_parallel_size=args.cfg_parallel_size
ulysses_degree=args.ulysses_degree,
ring_degree=args.ring_degree,
cfg_parallel_size=args.cfg_parallel_size,
tensor_parallel_size=args.tensor_parallel_size,
)
# Configure cache based on backend type
@@ -351,7 +360,7 @@ def main():
else:
print(f" Input image size: {input_image.size}")
print(
f" Parallel configuration: ulysses_degree={args.ulysses_degree}, ring_degree={args.ring_degree}, cfg_parallel_size={args.cfg_parallel_size}"
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}"
)
print(f"{'=' * 60}\n")