Skip to content

[Model] SupportHunyuanImage3 Diffusion Model in vllm-omni #1085

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hsliuustc0106 merged 1 commit into from
Feb 9, 2026
Merged

[Model] SupportHunyuanImage3 Diffusion Model in vllm-omni #1085

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/models/supported_models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ th {
| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` |
| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` |
| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` |
| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` |
| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` |
| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` |
| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` |
Expand Down
1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,6 +188,7 @@ extend-ignore-identifiers-re = [
".*arange",
".*MoBA",
".*temperal_downsample",
".*_nd",
".*nothink.*",
".*NOTHINK.*",
".*nin.*",
Expand Down
2 changes: 2 additions & 0 deletions vllm_omni/diffusion/distributed/parallel_state.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -757,6 +757,7 @@ def initialize_model_parallel(
backend=backend,
parallel_mode="data",
)
vllm_parallel_state._DP = _DP
Copy link
Contributor

@Semmer2 Semmer2 Jan 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

double check if this code necessary


global _CFG
assert _CFG is None, "classifier_free_guidance group is already initialized"
Expand All @@ -774,6 +775,7 @@ def initialize_model_parallel(
backend=backend,
parallel_mode="pipeline",
)
vllm_parallel_state._PP = _PP

global _SP
assert _SP is None, "sequence parallel group is already initialized"
Expand Down
17 changes: 17 additions & 0 deletions vllm_omni/diffusion/models/hunyuan_image_3/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Hunyuan Image 3 diffusion model components."""

from vllm_omni.diffusion.models.hunyuan_image_3.hunyuan_image_3_transformer import (
HunyuanImage3Model,
HunyuanImage3Text2ImagePipeline,
)
from vllm_omni.diffusion.models.hunyuan_image_3.pipeline_hunyuan_image_3 import (
HunyuanImage3Pipeline,
)

__all__ = [
"HunyuanImage3Pipeline",
"HunyuanImage3Model",
"HunyuanImage3Text2ImagePipeline",
]
Loading