[Feature] Support DiT Layerwise (Blockwise) CPU Offloading (#858)

Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-01-30 17:35:09 +08:00
1 parent be580d5c24
commit 2923d5a91e
14 files changed
+613 -41

No files matched your search

@@ -295,6 +295,17 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable CPU offloading for diffusion models.",
)
parser.add_argument(
"--enable-layerwise-offload",
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--layerwise-num-gpu-layers",
type=int,
default=1,
help="Number of ready layers (blocks) to keep on GPU during generation.",
)
return parser.parse_args()
@@ -350,6 +361,8 @@ def main():
# Initialize Omni with appropriate pipeline
omni = Omni(
model=args.model,
enable_layerwise_offload=args.enable_layerwise_offload,
layerwise_num_gpu_layers=args.layerwise_num_gpu_layers,
vae_use_slicing=args.vae_use_slicing,
vae_use_tiling=args.vae_use_tiling,
cache_backend=args.cache_backend,
@@ -74,6 +74,17 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable CPU offloading for diffusion models.",
)
parser.add_argument(
"--enable-layerwise-offload",
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--layerwise-num-gpu-layers",
type=int,
default=1,
help="Number of ready layers (blocks) to keep on GPU during generation.",
)
return parser.parse_args()
@@ -112,6 +123,8 @@ def main():
omni = Omni(
model=args.model,
enable_layerwise_offload=args.enable_layerwise_offload,
layerwise_num_gpu_layers=args.layerwise_num_gpu_layers,
vae_use_slicing=args.vae_use_slicing,
vae_use_tiling=args.vae_use_tiling,
boundary_ratio=args.boundary_ratio,
@@ -107,6 +107,17 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable CPU offloading for diffusion models.",
)
parser.add_argument(
"--enable-layerwise-offload",
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--layerwise-num-gpu-layers",
type=int,
default=1,
help="Number of ready layers (blocks) to keep on GPU during generation.",
)
parser.add_argument(
"--tensor_parallel_size",
type=int,
@@ -172,6 +183,8 @@ def main():
omni = Omni(
model=args.model,
enable_layerwise_offload=args.enable_layerwise_offload,
layerwise_num_gpu_layers=args.layerwise_num_gpu_layers,
vae_use_slicing=args.vae_use_slicing,
vae_use_tiling=args.vae_use_tiling,
cache_backend=args.cache_backend,
@@ -79,6 +79,17 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable CPU offloading for diffusion models.",
)
parser.add_argument(
"--enable-layerwise-offload",
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--layerwise-num-gpu-layers",
type=int,
default=1,
help="Number of ready layers (blocks) to keep on GPU during generation.",
)
parser.add_argument(
"--ulysses_degree",
type=int,
@@ -128,6 +139,8 @@ def main():
omni = Omni(
model=args.model,
enable_layerwise_offload=args.enable_layerwise_offload,
layerwise_num_gpu_layers=args.layerwise_num_gpu_layers,
vae_use_slicing=args.vae_use_slicing,
vae_use_tiling=args.vae_use_tiling,
boundary_ratio=args.boundary_ratio,