add qwen3

vllm-v0.6.2/vllm/assets/audio.py

@@ -0,0 +1,28 @@
+from dataclasses import dataclass
+from typing import Literal, Tuple
+from urllib.parse import urljoin
+
+import librosa
+import numpy as np
+
+from vllm.assets.base import get_vllm_public_assets, vLLM_S3_BUCKET_URL
+
+ASSET_DIR = "multimodal_asset"
+
+
+@dataclass(frozen=True)
+class AudioAsset:
+    name: Literal["winning_call", "mary_had_lamb"]
+
+    @property
+    def audio_and_sample_rate(self) -> Tuple[np.ndarray, int]:
+
+        audio_path = get_vllm_public_assets(filename=f"{self.name}.ogg",
+                                            s3_prefix=ASSET_DIR)
+        y, sr = librosa.load(audio_path, sr=None)
+        assert isinstance(sr, int)
+        return y, sr
+
+    @property
+    def url(self) -> str:
+        return urljoin(vLLM_S3_BUCKET_URL, f"{ASSET_DIR}/{self.name}.ogg")

vllm-v0.6.2/vllm/assets/base.py

@@ -0,0 +1,39 @@
+from functools import lru_cache
+from pathlib import Path
+from typing import Optional
+
+import vllm.envs as envs
+from vllm.connections import global_http_connection
+from vllm.envs import VLLM_IMAGE_FETCH_TIMEOUT
+
+vLLM_S3_BUCKET_URL = "https://vllm-public-assets.s3.us-west-2.amazonaws.com"
+
+
+def get_cache_dir() -> Path:
+    """Get the path to the cache for storing downloaded assets."""
+    path = Path(envs.VLLM_ASSETS_CACHE)
+    path.mkdir(parents=True, exist_ok=True)
+
+    return path
+
+
+@lru_cache
+def get_vllm_public_assets(filename: str,
+                           s3_prefix: Optional[str] = None) -> Path:
+    """
+    Download an asset file from ``s3://vllm-public-assets``
+    and return the path to the downloaded file.
+    """
+    asset_directory = get_cache_dir() / "vllm_public_assets"
+    asset_directory.mkdir(parents=True, exist_ok=True)
+
+    asset_path = asset_directory / filename
+    if not asset_path.exists():
+        if s3_prefix is not None:
+            filename = s3_prefix + "/" + filename
+        global_http_connection.download_file(
+            f"{vLLM_S3_BUCKET_URL}/{filename}",
+            asset_path,
+            timeout=VLLM_IMAGE_FETCH_TIMEOUT)
+
+    return asset_path

vllm-v0.6.2/vllm/assets/image.py

@@ -0,0 +1,30 @@
+from dataclasses import dataclass
+from typing import Literal
+
+import torch
+from PIL import Image
+
+from vllm.assets.base import get_vllm_public_assets
+
+VLM_IMAGES_DIR = "vision_model_images"
+
+
+@dataclass(frozen=True)
+class ImageAsset:
+    name: Literal["stop_sign", "cherry_blossom"]
+
+    @property
+    def pil_image(self) -> Image.Image:
+
+        image_path = get_vllm_public_assets(filename=f"{self.name}.jpg",
+                                            s3_prefix=VLM_IMAGES_DIR)
+        return Image.open(image_path)
+
+    @property
+    def image_embeds(self) -> torch.Tensor:
+        """
+        Image embeddings, only used for testing purposes with llava 1.5.
+        """
+        image_path = get_vllm_public_assets(filename=f"{self.name}.pt",
+                                            s3_prefix=VLM_IMAGES_DIR)
+        return torch.load(image_path, map_location="cpu")

vllm-v0.6.2/vllm/assets/video.py

@@ -0,0 +1,85 @@
+from dataclasses import dataclass
+from functools import lru_cache
+from typing import List, Literal
+
+import numpy as np
+import numpy.typing as npt
+from huggingface_hub import hf_hub_download
+from PIL import Image
+
+from vllm.multimodal.utils import (sample_frames_from_video,
+                                   try_import_video_packages)
+
+from .base import get_cache_dir
+
+
+@lru_cache
+def download_video_asset(filename: str) -> str:
+    """
+    Download and open an image from huggingface
+    repo: raushan-testing-hf/videos-test
+    """
+    video_directory = get_cache_dir() / "video-eample-data"
+    video_directory.mkdir(parents=True, exist_ok=True)
+
+    video_path = video_directory / filename
+    video_path_str = str(video_path)
+    if not video_path.exists():
+        video_path_str = hf_hub_download(
+            repo_id="raushan-testing-hf/videos-test",
+            filename=filename,
+            repo_type="dataset",
+            cache_dir=video_directory,
+        )
+    return video_path_str
+
+
+def video_to_ndarrays(path: str, num_frames: int = -1) -> npt.NDArray:
+    cv2, _ = try_import_video_packages()
+
+    cap = cv2.VideoCapture(path)
+    if not cap.isOpened():
+        raise ValueError(f"Could not open video file {path}")
+
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    frames = []
+    for i in range(total_frames):
+        ret, frame = cap.read()
+        if ret:
+            frames.append(frame)
+    cap.release()
+
+    frames = np.stack(frames)
+    frames = sample_frames_from_video(frames, num_frames)
+    if len(frames) < num_frames:
+        raise ValueError(f"Could not read enough frames from video file {path}"
+                         f" (expected {num_frames} frames, got {len(frames)})")
+    return frames
+
+
+def video_to_pil_images_list(path: str,
+                             num_frames: int = -1) -> List[Image.Image]:
+    cv2, _ = try_import_video_packages()
+    frames = video_to_ndarrays(path, num_frames)
+    return [
+        Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+        for frame in frames
+    ]
+
+
+@dataclass(frozen=True)
+class VideoAsset:
+    name: Literal["sample_demo_1.mp4"]
+    num_frames: int = -1
+
+    @property
+    def pil_images(self) -> List[Image.Image]:
+        video_path = download_video_asset(self.name)
+        ret = video_to_pil_images_list(video_path, self.num_frames)
+        return ret
+
+    @property
+    def np_ndarrays(self) -> npt.NDArray:
+        video_path = download_video_asset(self.name)
+        ret = video_to_ndarrays(video_path, self.num_frames)
+        return ret