[model]Add UltraFlux-v1-image support

docs/models/supported_models.md

@@ -37,10 +37,7 @@ th {
 |`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` |
-|`Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-0.6B-Base` |
-
+|`UltraFluxPipeline` | UltraFlux-v1 | `Owen777/UltraFlux-v1` |
 
 ## List of Supported Models for NPU
 

vllm_omni/diffusion/cache/cache_dit_backend.py

@@ -346,6 +346,55 @@ def refresh_cache_context(pipeline: Any, num_inference_steps: int, verbose: bool
     return refresh_cache_context
 
 
+def enable_cache_for_ultraflux(pipeline: Any, cache_config: Any) -> Callable[[int], None]:
+    db_cache_config = _build_db_cache_config(cache_config)
+
+    calibrator = None
+    if cache_config.enable_taylorseer:
+        taylorseer_order = cache_config.taylorseer_order
+        calibrator = TaylorSeerCalibratorConfig(taylorseer_order=taylorseer_order)
+        logger.info(f"TaylorSeer enabled with order={taylorseer_order}")
+
+    modifier = ParamsModifier(cache_config=db_cache_config, calibrator_config=calibrator)
+
+    logger.info(
+        "Enabling cache-dit on Flux transformer blocks with BlockAdapter: "
+        f"Fn={db_cache_config.Fn_compute_blocks}, "
+        f"Bn={db_cache_config.Bn_compute_blocks}, "
+        f"W={db_cache_config.max_warmup_steps}, "
+    )
+
+    transformer = pipeline.transformer
+    cache_dit.enable_cache(
+        BlockAdapter(
+            transformer=transformer,
+            blocks=[transformer.transformer_blocks, transformer.single_transformer_blocks],
+            forward_pattern=[ForwardPattern.Pattern_1, ForwardPattern.Pattern_1],
+            params_modifiers=[modifier],
+        ),
+        cache_config=db_cache_config,
+    )
+
+    def refresh_cache_context(pipeline: Any, num_inference_steps: int, verbose: bool = True) -> None:
+        if cache_config.scm_steps_mask_policy is None:
+            cache_dit.refresh_context(pipeline.transformer, num_inference_steps=num_inference_steps, verbose=verbose)
+        else:
+            cache_dit.refresh_context(
+                pipeline.transformer,
+                cache_config=DBCacheConfig().reset(
+                    num_inference_steps=num_inference_steps,
+                    steps_computation_mask=cache_dit.steps_mask(
+                        mask_policy=cache_config.scm_steps_mask_policy,
+                        total_steps=num_inference_steps,
+                    ),
+                    steps_computation_policy=cache_config.scm_steps_policy,
+                ),
+                verbose=verbose,
+            )
+
+    return refresh_cache_context
+
+
 def enable_cache_for_sd3(pipeline: Any, cache_config: Any) -> Callable[[int], None]:
     """Enable cache-dit for StableDiffusion3Pipeline.
 
@@ -859,8 +908,9 @@ def refresh_cache_context(pipeline: Any, num_inference_steps: int, verbose: bool
         "Wan22I2VPipeline": enable_cache_for_wan22,
         "Wan22TI2VPipeline": enable_cache_for_wan22,
         "FluxPipeline": enable_cache_for_flux,
-        "LongCatImagePipeline": enable_cache_for_longcat_image,
-        "LongCatImageEditPipeline": enable_cache_for_longcat_image,
+        "UltraFluxPipeline": enable_cache_for_ultraflux,
+        "LongcatImagePipeline": enable_cache_for_longcat_image,
+        "LongcatImageEditPipeline": enable_cache_for_longcat_image,
         "StableDiffusion3Pipeline": enable_cache_for_sd3,
         "BagelPipeline": enable_cache_for_bagel,
     }
@@ -978,4 +1028,5 @@ def may_enable_cache_dit(pipeline: Any, od_config: OmniDiffusionConfig) -> Optio
 
     backend = CacheDiTBackend(od_config.cache_config)
     backend.enable(pipeline)
+
     return backend if backend.is_enabled() else None

vllm_omni/diffusion/models/ultraflux-v1_image/__init__.py

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# UltraFlux diffusion model integration for vLLM-Omni
+
+from .pipeline_ultraflux import UltraFluxPipeline
+
+__all__ = [
+    "UltraFluxPipeline",
+]