[XPU] update Dreamzero to support any HW (#4399)

Signed-off-by: Chendi Xue <chendi.xue@intel.com>
This commit is contained in:
Chendi.Xue authored and GitHub committed 2026-06-13 15:32:39 +00:00
1 parent 31886d6ece
commit a9ee92ddec
3 files changed
+6 -5

No files matched your search

+1 -1
View File
@@ -42,7 +42,7 @@ th {
| `LTX2ImageToVideoTwoStagesPipeline` | LTX-2-I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | |
| `LTX23Pipeline` | LTX-2.3-T2V | `dg845/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | |
| `LTX23ImageToVideoPipeline` | LTX-2.3-I2V | `dg845/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | |
| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | | | |
| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | |
| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | |
| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ |
@@ -617,6 +617,8 @@ class CausalWanModel(nn.Module):
Architecture (14B): 40 layers, dim=5120, heads=40, ffn=13824
"""
_layerwise_offload_blocks_attrs = ["blocks"]
def __init__(
self,
model_type: str = "t2v",
@@ -49,6 +49,7 @@ from vllm_omni.diffusion.models.dreamzero.utils import (
)
from vllm_omni.diffusion.models.schedulers.scheduling_flow_unipc_multistep import FlowUniPCMultistepScheduler
from vllm_omni.diffusion.request import OmniDiffusionRequest
from vllm_omni.platforms import current_omni_platform
logger = logging.getLogger(__name__)
MAX_DREAMZERO_SESSIONS = 64
@@ -363,12 +364,10 @@ class DreamZeroPipeline(nn.Module, CFGParallelMixin):
latents: tuple[torch.Tensor, torch.Tensor],
do_true_cfg: bool,
) -> tuple[torch.Tensor, torch.Tensor]:
"""Post-step sync: .contiguous() + cuda.synchronize()"""
"""Post-step sync: .contiguous() + platform synchronize."""
latents = tuple(t.contiguous() for t in latents)
if do_true_cfg and get_classifier_free_guidance_world_size() > 1:
device = next((t.device for t in latents if t.is_cuda), None)
if device is not None:
torch.cuda.current_stream(device).synchronize()
current_omni_platform.synchronize()
return latents
# -----------------------------------------------------------------------