[chore] refine the examples (#3095)

Signed-off-by: Lancer <maruixiang6688@gmail.com>
This commit is contained in:
Lancer authored and GitHub committed 2026-04-24 13:40:38 +08:00
1 parent 9ebfbf9fde
commit d20a6b5b39
4 files changed
+109

No files matched your search

@@ -196,6 +196,13 @@ def parse_args() -> argparse.Namespace:
default=1,
help="Number of GPUs used for ulysses sequence parallelism.",
)
parser.add_argument(
"--ulysses-mode",
type=str,
default="strict",
choices=["strict", "advanced_uaa"],
help="Ulysses sequence-parallel mode: 'strict' (divisibility required) or 'advanced_uaa' (UAA).",
)
parser.add_argument(
"--ring-degree",
type=int,
@@ -325,6 +332,29 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--vae-patch-parallel-size",
type=int,
default=1,
help="Number of GPUs used for VAE patch/tile parallelism (decode).",
)
parser.add_argument(
"--use-hsdp",
action="store_true",
help="Enable HSDP (Hybrid Sharded Data Parallel) for diffusion models.",
)
parser.add_argument(
"--hsdp-shard-size",
type=int,
default=1,
help="Number of GPUs to shard weights across for HSDP.",
)
parser.add_argument(
"--hsdp-replicate-size",
type=int,
default=1,
help="Number of HSDP replica groups.",
)
parser.add_argument(
"--enable-diffusion-pipeline-profiler",
action="store_true",
@@ -131,6 +131,44 @@ def parse_args() -> argparse.Namespace:
default=1,
help="Number of HSDP replica groups. Default 1 means pure sharding.",
)
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(
"--ulysses-degree",
type=int,
default=1,
help="Number of GPUs used for ulysses sequence parallelism.",
)
parser.add_argument(
"--ulysses-mode",
type=str,
default="strict",
choices=["strict", "advanced_uaa"],
help="Ulysses sequence-parallel mode: 'strict' (divisibility required) or 'advanced_uaa' (UAA).",
)
parser.add_argument(
"--ring-degree",
type=int,
default=1,
help="Number of GPUs used for ring sequence parallelism.",
)
parser.add_argument(
"--cfg-parallel-size",
type=int,
default=1,
choices=[1, 2],
help="Number of GPUs used for classifier free guidance parallel size.",
)
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()
@@ -144,6 +144,23 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--use-hsdp",
action="store_true",
help="Enable HSDP (Hybrid Sharded Data Parallel) for diffusion models.",
)
parser.add_argument(
"--hsdp-shard-size",
type=int,
default=1,
help="Number of GPUs to shard weights across for HSDP.",
)
parser.add_argument(
"--hsdp-replicate-size",
type=int,
default=1,
help="Number of HSDP replica groups.",
)
parser.add_argument(
"--quantization",
type=str,
@@ -131,6 +131,13 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable layerwise (blockwise) offloading on DiT modules.",
)
parser.add_argument(
"--ulysses-mode",
type=str,
default="strict",
choices=["strict", "advanced_uaa"],
help="Ulysses sequence-parallel mode: 'strict' (divisibility required) or 'advanced_uaa' (UAA).",
)
parser.add_argument(
"--ulysses-degree",
type=int,
@@ -185,6 +192,23 @@ def parse_args() -> argparse.Namespace:
choices=["fp8", "gguf"],
help="Quantization method for the transformer (fp8 for online FP8 quantization).",
)
parser.add_argument(
"--use-hsdp",
action="store_true",
help="Enable HSDP (Hybrid Sharded Data Parallel) for diffusion models.",
)
parser.add_argument(
"--hsdp-shard-size",
type=int,
default=1,
help="Number of GPUs to shard weights across for HSDP.",
)
parser.add_argument(
"--hsdp-replicate-size",
type=int,
default=1,
help="Number of HSDP replica groups.",
)
return parser.parse_args()