Dev/rebase 0.14.0 (#847)

Signed-off-by: JaredforReal <w13431838023@gmail.com>
Signed-off-by: root <root@hk01dgx039.cm.cluster>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: TangPeng <85704592@qq.com>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: iwzbi <wzbi@zju.edu.cn>
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
Signed-off-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com>
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: John Liu BUAA <liukecheng97@gmail.com>
Signed-off-by: Dinesh G <G.Dinesh@ibm.com>
Signed-off-by: gDINESH13 <dinesh13g@gmail.com>
Signed-off-by: root <root@hk01dgx028.cm.cluster>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: root <root@hk01dgx039.cm.cluster>
Co-authored-by: JustQJ <37905360+JustQJ@users.noreply.github.com>
Co-authored-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Co-authored-by: Sihyeon Jang <uneedsihyeon@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: catcat <108673086+iwzbi@users.noreply.github.com>
Co-authored-by: Ziming Huang <hzm414167@alibaba-inc.com>
Co-authored-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: John Liu BUAA <liukecheng97@gmail.com>
Co-authored-by: D!NE$H <67671800+gDINESH13@users.noreply.github.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>

examples/offline_inference/qwen2_5_omni/end2end.py

@@ -278,9 +278,9 @@ def get_audio_query(question: str = None, audio_path: str | None = None, samplin
 
 
 query_map = {
-    "mixed_modalities": get_mixed_modalities_query,
+    "use_mixed_modalities": get_mixed_modalities_query,
     "use_audio_in_video": get_use_audio_in_video_query,
-    "multi_audios": get_multi_audios_query,
+    "use_multi_audios": get_multi_audios_query,
     "use_image": get_image_query,
     "use_video": get_video_query,
     "use_audio": get_audio_query,
@@ -434,7 +434,7 @@ def parse_args():
         "--query-type",
         "-q",
         type=str,
-        default="mixed_modalities",
+        default="use_mixed_modalities",
         choices=query_map.keys(),
         help="Query type.",
     )

examples/offline_inference/qwen2_5_omni/run_single_prompt.sh

@@ -1,2 +1,2 @@
 python end2end.py --output-wav output_audio \
-                  --query-type mixed_modalities
+                  --query-type use_mixed_modalities

examples/offline_inference/qwen3_omni/end2end.py

@@ -12,6 +12,7 @@ from typing import NamedTuple
 import librosa
 import numpy as np
 import soundfile as sf
+import vllm
 from PIL import Image
 from vllm import SamplingParams
 from vllm.assets.audio import AudioAsset
@@ -225,18 +226,76 @@ def get_multi_audios_query() -> QueryResult:
     )
 
 
+# def get_use_audio_in_video_query(video_path: str | None = None) -> QueryResult:
+# question = (
+#     "Describe the content of the video in details, then convert what the "
+#     "baby say into text."
+# )
+# prompt = (
+#     f"<|im_start|>system\n{default_system}<|im_end|>\n"
+#     "<|im_start|>user\n<|vision_start|><|video_pad|><|vision_end|>"
+#     f"{question}<|im_end|>\n"
+#     f"<|im_start|>assistant\n"
+# )
+# if video_path:
+#     if not os.path.exists(video_path):
+#         raise FileNotFoundError(f"Video file not found: {video_path}")
+#     video_frames = video_to_ndarrays(video_path, num_frames=16)
+# else:
+#     video_frames = VideoAsset(name="baby_reading", num_frames=16).np_ndarrays
+# audio = extract_video_audio(video_path, sampling_rate=16000)
+# return QueryResult(
+#     inputs={
+#         "prompt": prompt,
+#         "multi_modal_data": {
+#             "video": video_frames,
+#             "audio": audio,
+#         },
+#         "mm_processor_kwargs": {
+#             "use_audio_in_video": True,
+#         },
+#     },
+#     limit_mm_per_prompt={"audio": 1, "video": 1},
+# )
+def get_use_audio_in_video_query() -> QueryResult:
+    question = "Describe the content of the video in details, then convert what the baby say into text."
+    prompt = (
+        f"<|im_start|>system\n{default_system}<|im_end|>\n"
+        "<|im_start|>user\n<|vision_start|><|video_pad|><|vision_end|>"
+        f"{question}<|im_end|>\n"
+        f"<|im_start|>assistant\n"
+    )
+    asset = VideoAsset(name="baby_reading", num_frames=16)
+    audio = asset.get_audio(sampling_rate=16000)
+    return QueryResult(
+        inputs={
+            "prompt": prompt,
+            "multi_modal_data": {
+                "video": asset.np_ndarrays,
+                "audio": audio,
+            },
+            "mm_processor_kwargs": {
+                "use_audio_in_video": True,
+            },
+        },
+        limit_mm_per_prompt={"audio": 1, "video": 1},
+    )
+
+
 query_map = {
     "text": get_text_query,
     "use_audio": get_audio_query,
     "use_image": get_image_query,
     "use_video": get_video_query,
-    "multi_audios": get_multi_audios_query,
-    "mixed_modalities": get_mixed_modalities_query,
+    "use_multi_audios": get_multi_audios_query,
+    "use_mixed_modalities": get_mixed_modalities_query,
+    "use_audio_in_video": get_use_audio_in_video_query,
 }
 
 
 def main(args):
     model_name = "Qwen/Qwen3-Omni-30B-A3B-Instruct"
+    print("=" * 20, "\n", f"vllm version: {vllm.__version__}", "\n", "=" * 20)
 
     # Get paths from args
     video_path = getattr(args, "video_path", None)
@@ -259,6 +318,10 @@ def main(args):
             num_frames=getattr(args, "num_frames", 16),
             sampling_rate=getattr(args, "sampling_rate", 16000),
         )
+    elif args.query_type == "multi_audios":
+        query_result = query_func()
+    elif args.query_type == "use_audio_in_video":
+        query_result = query_func()
     else:
         query_result = query_func()
 
@@ -270,7 +333,7 @@ def main(args):
     )
 
     thinker_sampling_params = SamplingParams(
-        temperature=0.4,
+        temperature=0.9,
         top_p=0.9,
         top_k=-1,
         max_tokens=1200,
@@ -331,6 +394,8 @@ def main(args):
     total_requests = len(prompts)
     processed_count = 0
 
+    print(f"query type: {args.query_type}")
+
     for stage_outputs in omni_generator:
         if stage_outputs.final_output_type == "text":
             for output in stage_outputs.request_output:
@@ -385,7 +450,7 @@ def parse_args():
         "--query-type",
         "-q",
         type=str,
-        default="mixed_modalities",
+        default="use_mixed_modalities",
         choices=query_map.keys(),
         help="Query type.",
     )

examples/online_serving/qwen3_omni/openai_chat_completion_client_for_multimodal_generation.py

@@ -305,6 +305,26 @@ def get_multi_audios_query(custom_prompt: str | None = None):
     }
 
 
+def get_use_audio_in_video_query(
+    video_path: str | None = None,
+    audio_path: str | None = None,
+    custom_prompt: str | None = None,
+):
+    question = custom_prompt or (
+        "Describe the content of the video in details, then convert what the baby say into text."
+    )
+    video_url = get_video_url_from_path(video_path)
+    audio_url = get_audio_url_from_path(audio_path)
+    return {
+        "role": "user",
+        "content": [
+            {"type": "video_url", "video_url": {"url": video_url}},
+            {"type": "audio_url", "audio_url": {"url": audio_url}},
+            {"type": "text", "text": question},
+        ],
+    }
+
+
 query_map = {
     "text": get_text_query,
     "use_audio": get_audio_query,
@@ -312,6 +332,7 @@ query_map = {
     "use_video": get_video_query,
     "use_mixed_modalities": get_mixed_modalities_query,
     "use_multi_audios": get_multi_audios_query,
+    "use_audio_in_video": get_use_audio_in_video_query,
 }
 
 
@@ -372,6 +393,12 @@ def run_multimodal_generation(args) -> None:
         prompt = query_func(audio_path=audio_path, custom_prompt=custom_prompt)
     elif args.query_type == "text":
         prompt = query_func(custom_prompt=custom_prompt)
+    elif args.query_type == "use_audio_in_video":
+        prompt = query_func(
+            video_path=video_path,
+            audio_path=audio_path,
+            custom_prompt=custom_prompt,
+        )
     else:
         prompt = query_func()