[Model]: add FLUX.1-dev model (vllm-project#853)

Author: nuclearwu

docs/models/supported_models.md

@@ -33,6 +33,7 @@ th {
 |`LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` |
 |`StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` |
 |`Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` |
+|`FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` |
 |`StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` |
 |`Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` |
 |`Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` |

docs/user_guide/diffusion/parallelism_acceleration.md

@@ -30,6 +30,7 @@ The following table shows which models are currently supported by parallelism me
 | **Z-Image** | `Tongyi-MAI/Z-Image-Turbo` | ✅ | ✅ | ❌ | ✅ (TP=2 only) |
 | **Stable-Diffusion3.5** | `stabilityai/stable-diffusion-3.5` | ❌ | ❌ | ❌ | ❌ |
 | **FLUX.2-klein** | `black-forest-labs/FLUX.2-klein-4B` | ❌ | ❌ | ❌ | ✅ |
+| **FLUX.1-dev** | `black-forest-labs/FLUX.1-dev` | ❌ | ❌ | ❌ | ✅ |
 
 
 !!! note "TP Limitations for Diffusion Models"

vllm_omni/diffusion/cache/cache_dit_backend.py

@@ -791,7 +791,7 @@ def refresh_cache_context(pipeline: Any, num_inference_steps: int, verbose: bool
 CUSTOM_DIT_ENABLERS.update(
     {
         "WanPipeline": enable_cache_for_wan22,
-        "FluxPipeline": enable_cache_for_flux,
+        # "FluxPipeline": enable_cache_for_flux,
         "LongCatImagePipeline": enable_cache_for_longcat_image,
         "LongCatImageEditPipeline": enable_cache_for_longcat_image,
         "StableDiffusion3Pipeline": enable_cache_for_sd3,

vllm_omni/diffusion/models/flux/__init__.py

@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""FLUX.1-dev diffusion model components."""
+
+from vllm_omni.diffusion.models.flux.flux_transformer import (
+    FluxTransformer2DModel,
+)
+from vllm_omni.diffusion.models.flux.pipeline_flux import (
+    FluxPipeline,
+    get_flux_post_process_func,
+)
+
+__all__ = [
+    "FluxPipeline",
+    "FluxTransformer2DModel",
+    "get_flux_post_process_func",
+]