Update test-merge.yml

Signed-off-by: Kevin H. Luu <khluu000@gmail.com>

docker/Dockerfile.rocm

@@ -1,4 +1,4 @@
-ARG BASE_IMAGE=vllm/vllm-openai-rocm:v0.15.0
+ARG BASE_IMAGE=vllm/vllm-openai-rocm:v0.16.0
 FROM ${BASE_IMAGE} AS base
 
 # Declare a variable to know if we want to use the nightly build or the stable build.
@@ -9,7 +9,7 @@ FROM ${BASE_IMAGE} AS base
 # 2. Whenever vLLM upstream has released a stable version,
 #    we should swap over to use stable release ASAP.
 #    We should avoid relying on custom commits.
-ARG USE_NIGHTLY_BUILD=1
+ARG USE_NIGHTLY_BUILD=0
 ARG VLLM_VERSION_OR_COMMIT_HASH=2d5be1dd5ce2e44dfea53ea03ff61143da5137eb
 ARG ARG_PYTORCH_ROCM_ARCH
 ENV PYTORCH_ROCM_ARCH=${ARG_PYTORCH_ROCM_ARCH:-${PYTORCH_ROCM_ARCH}}

docs/getting_started/installation/gpu/rocm.inc.md

@@ -13,7 +13,7 @@ vLLM-Omni current recommends the steps in under setup through Docker Images.
 
 vLLM-Omni is built based on vLLM. Please install it with command below.
 ```bash
-uv pip install vllm==0.14.0+rocm700 --extra-index-url https://wheels.vllm.ai/rocm/0.14.0/rocm700
+uv pip install vllm==0.16.0+rocm700 --extra-index-url https://wheels.vllm.ai/rocm/0.16.0/rocm700
 ```
 
 #### Installation of vLLM-Omni
@@ -34,13 +34,13 @@ uv pip install onnxruntime-rocm sox
 # --8<-- [start:build-wheel-from-source]
 
 #### Installation of vLLM
-If you do not need to modify source code of vLLM, you can directly install the stable 0.14.0 release version of the library
+If you do not need to modify source code of vLLM, you can directly install the stable 0.16.0 release version of the library
 
 ```bash
-uv pip install vllm==0.14.0+rocm700 --extra-index-url https://wheels.vllm.ai/rocm/0.14.0/rocm700
+uv pip install vllm==0.16.0+rocm700 --extra-index-url https://wheels.vllm.ai/rocm/0.16.0/rocm700
 ```
 
-The release 0.14.0 of vLLM requires ROCm 7.0 environment.
+The release 0.16.0 of vLLM requires ROCm 7.0 environment.
 
 #### Installation of vLLM-Omni
 Since vllm-omni is rapidly evolving, it's recommended to install it from source
@@ -58,7 +58,7 @@ If you want to check, modify or debug with source code of vLLM, install the libr
 ```bash
 git clone https://github.com/vllm-project/vllm.git
 cd vllm
-git checkout v0.14.0
+git checkout v0.16.0
 python3 -m pip install -r requirements/rocm.txt
 python3 setup.py develop
 ```

docs/models/supported_models.md

@@ -36,6 +36,7 @@ th {
 |`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` |
+|`OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` |
 |`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` |

examples/offline_inference/image_to_image/image_edit.py

@@ -2,6 +2,23 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 """
+Example script for image editing with OmniGen2.
+
+    python image_edit.py \
+        --image input.png \
+        --model "OmniGen2/OmniGen2" \
+        --prompt "Change the background to classroom." \
+        --negative-prompt "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar" \
+        --num-inference-steps 50 \
+        --seed 0 \
+        --guidance-scale 5.0 \
+        --guidance-scale-2 2.0 \
+        --output outputs/image_edit.png \
+        --num-outputs-per-prompt 2
+
+    Note: For OmniGen2, `guidance_scale` works as `text_guidance_scale`,
+    and `guidance_scale_2` works as `image_guidance_scale`.
+
 Example script for image editing with Qwen-Image-Edit.
 
 Usage (single image):
@@ -141,6 +158,9 @@ def parse_args() -> argparse.Namespace:
             "directly as an input parameter. Enabled when guidance_scale > 1. Ignored when not using guidance-distilled models."
         ),
     )
+    parser.add_argument(
+        "--guidance-scale-2", type=float, default=None, help="image guidance scale for image-to-image generation."
+    )
     parser.add_argument(
         "--output",
         type=str,
@@ -403,6 +423,7 @@ def main():
             generator=generator,
             true_cfg_scale=args.cfg_scale,
             guidance_scale=args.guidance_scale,
+            guidance_scale_2=args.guidance_scale_2,
             num_inference_steps=args.num_inference_steps,
             num_outputs_per_prompt=args.num_outputs_per_prompt,
             layers=args.layers,

vllm_omni/diffusion/registry.py

@@ -105,6 +105,11 @@ _DIFFUSION_MODELS = {
         "pipeline_flux",
         "FluxPipeline",
     ),
+    "OmniGen2Pipeline": (
+        "omnigen2",
+        "pipeline_omnigen2",
+        "OmniGen2Pipeline",
+    ),
 }
 
 
@@ -289,6 +294,7 @@ _DIFFUSION_POST_PROCESS_FUNCS = {
     "Flux2KleinPipeline": "get_flux2_klein_post_process_func",
     "NextStep11Pipeline": "get_nextstep11_post_process_func",
     "FluxPipeline": "get_flux_post_process_func",
+    "OmniGen2Pipeline": "get_omnigen2_post_process_func",
 }
 
 _DIFFUSION_PRE_PROCESS_FUNCS = {
@@ -302,6 +308,7 @@ _DIFFUSION_PRE_PROCESS_FUNCS = {
     "QwenImageLayeredPipeline": "get_qwen_image_layered_pre_process_func",
     "WanPipeline": "get_wan22_pre_process_func",
     "WanImageToVideoPipeline": "get_wan22_i2v_pre_process_func",
+    "OmniGen2Pipeline": "get_omnigen2_pre_process_func",
 }
 
 

vllm_omni/model_executor/models/qwen3_tts/qwen3_tts_tokenizer.py

@@ -328,7 +328,7 @@ class Qwen3TTSTokenizer:
         else:
             # List[Tensor/np]
             audio_codes_list = [_to_tensor(c, dtype=torch.long) for c in audio_codes_list]
-            audio_codes_padded = pad_sequence(audio_codes_list, batch_first=True, padding_value=0).to(self.device)
+            audio_codes_padded = pad_sequence(audio_codes_list, batch_first=True, padding_value=-1).to(self.device)
 
         with torch.inference_mode():
             if model_type == "qwen3_tts_tokenizer_25hz":

vllm_omni/model_executor/models/qwen3_tts/tokenizer_12hz/modeling_qwen3_tts_tokenizer_v2.py

@@ -991,10 +991,11 @@ class Qwen3TTSTokenizerV2Model(Qwen3TTSTokenizerV2PreTrainedModel):
 
         """
         return_dict = return_dict if return_dict is not None else self.config.return_dict
+        audio_lengths = (audio_codes[..., 0] > -1).sum(1) * self.decode_upsample_rate
 
+        audio_codes = torch.clamp(audio_codes, min=0)
         audio_values = self.decoder.chunked_decode(audio_codes.transpose(1, 2)).squeeze(1)
 
-        audio_lengths = (audio_codes[..., 0] > 0).sum(1) * self.decode_upsample_rate
         audio_values = [a[:length] for a, length in zip(audio_values, audio_lengths)]
 
         if not return_dict:

vllm_omni/model_executor/models/qwen3_tts/tokenizer_25hz/modeling_qwen3_tts_tokenizer_v1.py

@@ -1508,10 +1508,11 @@ class Qwen3TTSTokenizerV1Model(Qwen3TTSTokenizerV1PreTrainedModel):
 
         """
         return_dict = return_dict if return_dict is not None else self.config.return_dict
+        audio_lengths = (audio_codes > -1).sum(1) * self.decode_upsample_rate
 
+        audio_codes = torch.clamp(audio_codes, min=0)
         audio_values = self.decoder(code=audio_codes, reference_mel=ref_mels, conditioning=xvectors)
 
-        audio_lengths = (audio_codes > 0).sum(1) * self.decode_upsample_rate
         audio_values = [a[:length] for a, length in zip(audio_values, audio_lengths)]
 
         if not return_dict: