vllm-cpu 0.9.2.post2__cp311-cp311-manylinux_2_17_aarch64.whl

vllm/assets/audio.py

@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Literal
+from urllib.parse import urljoin
+
+import numpy.typing as npt
+
+from vllm.utils import PlaceholderModule
+
+from .base import VLLM_S3_BUCKET_URL, get_vllm_public_assets
+
+try:
+    import librosa
+except ImportError:
+    librosa = PlaceholderModule("librosa")  # type: ignore[assignment]
+
+ASSET_DIR = "multimodal_asset"
+
+AudioAssetName = Literal["winning_call", "mary_had_lamb"]
+
+
+@dataclass(frozen=True)
+class AudioAsset:
+    name: AudioAssetName
+
+    @property
+    def filename(self) -> str:
+        return f"{self.name}.ogg"
+
+    @property
+    def audio_and_sample_rate(self) -> tuple[npt.NDArray, float]:
+        audio_path = get_vllm_public_assets(filename=self.filename,
+                                            s3_prefix=ASSET_DIR)
+        return librosa.load(audio_path, sr=None)
+
+    def get_local_path(self) -> Path:
+        return get_vllm_public_assets(filename=self.filename,
+                                      s3_prefix=ASSET_DIR)
+
+    @property
+    def url(self) -> str:
+        return urljoin(VLLM_S3_BUCKET_URL, f"{ASSET_DIR}/{self.name}.ogg")

vllm/assets/base.py

@@ -0,0 +1,41 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+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
+
+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=envs.VLLM_IMAGE_FETCH_TIMEOUT)
+
+    return asset_path

vllm/assets/image.py

@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from dataclasses import dataclass
+from typing import Literal
+
+import torch
+from PIL import Image
+
+from .base import get_vllm_public_assets
+
+VLM_IMAGES_DIR = "vision_model_images"
+
+ImageAssetName = Literal["stop_sign", "cherry_blossom"]
+
+
+@dataclass(frozen=True)
+class ImageAsset:
+    name: ImageAssetName
+
+    @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", weights_only=True)

vllm/assets/video.py

@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from dataclasses import dataclass
+from functools import lru_cache
+from typing import Any, ClassVar, Literal, Optional
+
+import cv2
+import numpy as np
+import numpy.typing as npt
+from huggingface_hub import hf_hub_download
+from PIL import Image
+
+from vllm.utils import PlaceholderModule
+
+from .base import get_cache_dir
+
+try:
+    import librosa
+except ImportError:
+    librosa = PlaceholderModule("librosa")  # type: ignore[assignment]
+
+
+@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-example-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:
+    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 = []
+
+    num_frames = num_frames if num_frames > 0 else total_frames
+    frame_indices = np.linspace(0, total_frames - 1, num_frames, dtype=int)
+    for idx in range(total_frames):
+        ok = cap.grab()  # next img
+        if not ok:
+            break
+        if idx in frame_indices:  # only decompress needed
+            ret, frame = cap.retrieve()
+            if ret:
+                frames.append(frame)
+
+    frames = np.stack(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]:
+    frames = video_to_ndarrays(path, num_frames)
+    return [
+        Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+        for frame in frames
+    ]
+
+
+def video_get_metadata(path: str) -> dict[str, Any]:
+    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))
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    duration = total_frames / fps if fps > 0 else 0
+
+    metadata = {
+        "total_num_frames": total_frames,
+        "fps": fps,
+        "duration": duration,
+        "video_backend": "opencv"
+    }
+    return metadata
+
+
+VideoAssetName = Literal["baby_reading"]
+
+
+@dataclass(frozen=True)
+class VideoAsset:
+    name: VideoAssetName
+    num_frames: int = -1
+
+    _NAME_TO_FILE: ClassVar[dict[VideoAssetName, str]] = {
+        "baby_reading": "sample_demo_1.mp4",
+    }
+
+    @property
+    def filename(self) -> str:
+        return self._NAME_TO_FILE[self.name]
+
+    @property
+    def pil_images(self) -> list[Image.Image]:
+        video_path = download_video_asset(self.filename)
+        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.filename)
+        ret = video_to_ndarrays(video_path, self.num_frames)
+        return ret
+
+    @property
+    def metadata(self) -> dict[str, Any]:
+        video_path = download_video_asset(self.filename)
+        ret = video_get_metadata(video_path)
+        return ret
+
+    def get_audio(self, sampling_rate: Optional[float] = None) -> npt.NDArray:
+        """
+        Read audio data from the video asset, used in Qwen2.5-Omni examples.
+        
+        See also: examples/offline_inference/qwen2_5_omni/only_thinker.py
+        """
+        video_path = download_video_asset(self.filename)
+        return librosa.load(video_path, sr=sampling_rate)[0]

vllm/attention/__init__.py

@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from vllm.attention.backends.abstract import (AttentionBackend,
+                                              AttentionMetadata,
+                                              AttentionMetadataBuilder,
+                                              AttentionState, AttentionType)
+from vllm.attention.layer import Attention
+from vllm.attention.selector import get_attn_backend
+
+__all__ = [
+    "Attention",
+    "AttentionBackend",
+    "AttentionMetadata",
+    "AttentionType",
+    "AttentionMetadataBuilder",
+    "Attention",
+    "AttentionState",
+    "get_attn_backend",
+]

vllm/attention/backends/abstract.py

@@ -0,0 +1,325 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from abc import ABC, abstractmethod
+from contextlib import contextmanager
+from dataclasses import dataclass, fields
+from typing import (TYPE_CHECKING, Any, Dict, Generic, List, Optional,
+                    Protocol, Set, Tuple, Type, TypeVar)
+
+import torch
+
+from vllm.multimodal import MultiModalPlaceholderMap
+
+if TYPE_CHECKING:
+    from vllm.worker.model_runner_base import (ModelRunnerBase,
+                                               ModelRunnerInputBase,
+                                               ModelRunnerInputBuilderBase)
+
+
+class AttentionType:
+    """
+    Attention type.
+    Use string to be compatible with `torch.compile`.
+    """
+    # Decoder attention between previous layer Q/K/V
+    DECODER = "decoder"
+    # Encoder attention between previous layer Q/K/V for encoder-decoder
+    ENCODER = "encoder"
+    # Encoder attention between previous layer Q/K/V
+    ENCODER_ONLY = "encoder_only"
+    # Attention between dec. Q and enc. K/V for encoder-decoder
+    ENCODER_DECODER = "encoder_decoder"
+
+
+class AttentionBackend(ABC):
+    """Abstract class for attention backends."""
+    # For some attention backends, we allocate an output tensor before
+    # calling the custom op. When piecewise cudagraph is enabled, this
+    # makes sure the output tensor is allocated inside the cudagraph.
+    accept_output_buffer: bool = False
+
+    @staticmethod
+    @abstractmethod
+    def get_name() -> str:
+        raise NotImplementedError
+
+    @staticmethod
+    @abstractmethod
+    def get_impl_cls() -> Type["AttentionImpl"]:
+        raise NotImplementedError
+
+    @staticmethod
+    @abstractmethod
+    def get_metadata_cls() -> Type["AttentionMetadata"]:
+        raise NotImplementedError
+
+    @staticmethod
+    @abstractmethod
+    def get_state_cls() -> Type["AttentionState"]:
+        raise NotImplementedError
+
+    @classmethod
+    def make_metadata(cls, *args, **kwargs) -> "AttentionMetadata":
+        return cls.get_metadata_cls()(*args, **kwargs)
+
+    @staticmethod
+    @abstractmethod
+    def get_builder_cls() -> Type["AttentionMetadataBuilder"]:
+        raise NotImplementedError
+
+    @staticmethod
+    @abstractmethod
+    def get_kv_cache_shape(
+        num_blocks: int,
+        block_size: int,
+        num_kv_heads: int,
+        head_size: int,
+    ) -> Tuple[int, ...]:
+        raise NotImplementedError
+
+    @staticmethod
+    def get_kv_cache_stride_order() -> Tuple[int, ...]:
+        raise NotImplementedError
+
+    @staticmethod
+    @abstractmethod
+    def swap_blocks(
+        src_kv_cache: torch.Tensor,
+        dst_kv_cache: torch.Tensor,
+        src_to_dst: torch.Tensor,
+    ) -> None:
+        raise NotImplementedError
+
+    @staticmethod
+    @abstractmethod
+    def copy_blocks(
+        kv_caches: List[torch.Tensor],
+        src_to_dists: torch.Tensor,
+    ) -> None:
+        raise NotImplementedError
+
+    def advance_step(self, model_input: "ModelRunnerInputBase",
+                     sampled_token_ids: Optional[torch.Tensor],
+                     block_size: int, num_seqs: int, num_queries: int) -> None:
+        raise NotImplementedError
+
+
+@dataclass
+class AttentionMetadata:
+    """Attention metadata for prefill and decode batched together."""
+    # Total number of prefill requests.
+    num_prefills: int
+    # Number of prefill tokens.
+    num_prefill_tokens: int
+    # Number of decode tokens. Note that it is equivalent to the number of
+    # decode requests.
+    num_decode_tokens: int
+    # (num_tokens,). The indices of the token slots that input tokens will be
+    # stored into. E.g., if `slot_mapping` is [35, 2, 17] and the block size
+    # is 16, the three tokens are stored in the 3rd slot in block 2, 2nd slot
+    # in block 0, and 1st slot in block 1, respectively.
+    slot_mapping: torch.Tensor
+
+    # The index maps that relate multi-modal embeddings to the corresponding
+    # placeholders.
+    #
+    # N.B. These aren't really related to attention and don't belong on this
+    # type -- this is just a temporary solution to make them available to
+    # `model_executable`.
+    multi_modal_placeholder_index_maps: Optional[Dict[
+        str, MultiModalPlaceholderMap.IndexMap]]
+
+    # Enable/disable KV scales calculation. This is so that we can disable the
+    # calculation until after prefill and cuda graph capture.
+    enable_kv_scales_calculation: bool
+
+    @property
+    @abstractmethod
+    def prefill_metadata(self) -> Optional["AttentionMetadata"]:
+        """Return the attention metadata that's required to run prefill
+        attention."""
+        pass
+
+    @property
+    @abstractmethod
+    def decode_metadata(self) -> Optional["AttentionMetadata"]:
+        """Return the attention metadata that's required to run decode
+        attention."""
+        pass
+
+    def asdict_zerocopy(self,
+                        skip_fields: Optional[Set[str]] = None
+                        ) -> Dict[str, Any]:
+        """Similar to dataclasses.asdict, but avoids deepcopying."""
+        if skip_fields is None:
+            skip_fields = set()
+        # Note that if we add dataclasses as fields, they will need
+        # similar handling.
+        return {
+            field.name: getattr(self, field.name)
+            for field in fields(self) if field.name not in skip_fields
+        }
+
+
+T = TypeVar("T", bound=AttentionMetadata)
+
+
+class AttentionState(ABC, Generic[T]):
+    """Holds attention backend-specific objects reused during the
+    lifetime of the model runner."""
+
+    @abstractmethod
+    def __init__(self, runner: "ModelRunnerBase"):
+        ...
+
+    @abstractmethod
+    @contextmanager
+    def graph_capture(self, max_batch_size: int):
+        """Context manager used when capturing CUDA graphs."""
+        yield
+
+    @abstractmethod
+    def graph_clone(self, batch_size: int) -> "AttentionState[T]":
+        """Clone attention state to save in CUDA graph metadata."""
+        ...
+
+    @abstractmethod
+    def graph_capture_get_metadata_for_batch(
+            self,
+            batch_size: int,
+            is_encoder_decoder_model: bool = False) -> T:
+        """Get attention metadata for CUDA graph capture of batch_size."""
+        ...
+
+    @abstractmethod
+    def get_graph_input_buffers(
+            self,
+            attn_metadata: T,
+            is_encoder_decoder_model: bool = False) -> Dict[str, Any]:
+        """Get attention-specific input buffers for CUDA graph capture."""
+        ...
+
+    @abstractmethod
+    def prepare_graph_input_buffers(
+            self,
+            input_buffers: Dict[str, Any],
+            attn_metadata: T,
+            is_encoder_decoder_model: bool = False) -> None:
+        """In-place modify input buffers dict for CUDA graph replay."""
+        ...
+
+    @abstractmethod
+    def begin_forward(self, model_input: "ModelRunnerInputBase") -> None:
+        """Prepare state for forward pass."""
+        ...
+
+
+class AttentionMetadataBuilder(ABC, Generic[T]):
+    """Abstract class for attention metadata builders."""
+
+    @abstractmethod
+    def __init__(self, input_builder: "ModelRunnerInputBuilderBase") -> None:
+        """Create the builder, remember some configuration and parameters."""
+        raise NotImplementedError
+
+    @abstractmethod
+    def prepare(self) -> None:
+        """Prepare for one batch."""
+        raise NotImplementedError
+
+    @abstractmethod
+    def build(self, seq_lens: List[int], query_lens: List[int],
+              cuda_graph_pad_size: int, batch_size: int) -> T:
+        """Build attention metadata with on-device tensors."""
+        raise NotImplementedError
+
+
+class AttentionLayer(Protocol):
+
+    _q_scale: torch.Tensor
+    _k_scale: torch.Tensor
+    _v_scale: torch.Tensor
+    _k_scale_float: float
+    _v_scale_float: float
+    _prob_scale: torch.Tensor
+
+    def forward(
+        self,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        value: torch.Tensor,
+        kv_cache: torch.Tensor,
+        attn_metadata: AttentionMetadata,
+    ) -> torch.Tensor:
+        ...
+
+
+class AttentionImpl(ABC, Generic[T]):
+
+    @abstractmethod
+    def __init__(
+        self,
+        num_heads: int,
+        head_size: int,
+        scale: float,
+        num_kv_heads: Optional[int] = None,
+        alibi_slopes: Optional[List[float]] = None,
+        sliding_window: Optional[int] = None,
+        kv_cache_dtype: str = "auto",
+        blocksparse_params: Optional[Dict[str, Any]] = None,
+        logits_soft_cap: Optional[float] = None,
+        attn_type: str = AttentionType.DECODER,
+        kv_sharing_target_layer_name: Optional[str] = None,
+    ) -> None:
+        raise NotImplementedError
+
+    @abstractmethod
+    def forward(
+        self,
+        layer: AttentionLayer,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        value: torch.Tensor,
+        kv_cache: torch.Tensor,
+        attn_metadata: T,
+        output: Optional[torch.Tensor] = None,
+        output_scale: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        raise NotImplementedError
+
+    def fused_output_quant_supported(self, dtype: torch.dtype, static: bool,
+                                     group_shape: tuple[int, int]):
+        """
+        Does this attention implementation support fused output quantization.
+        This is used by the AttnFusionPass to only fuse output quantization
+        onto implementations that support it.
+
+        TODO(luka) merge parameters into QuantDescriptor
+        :param dtype: quantized dtype
+        :param static: static or dynamic quantization
+        :param group_shape: quant group shape. (-1, -1) for per-tensor.
+        :return: is fusion supported for this type of quantization
+        """
+        return False
+
+
+class MLAAttentionImpl(AttentionImpl[T], Generic[T]):
+
+    @abstractmethod
+    def forward(
+        self,
+        layer: AttentionLayer,
+        hidden_states_or_cq: torch.Tensor,
+        kv_c_normed: torch.Tensor,
+        k_pe: torch.Tensor,
+        kv_cache: torch.Tensor,
+        attn_metadata: T,
+        output: Optional[torch.Tensor] = None,
+        output_scale: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        raise NotImplementedError
+
+
+def is_quantized_kv_cache(kv_cache_dtype: str) -> bool:
+    return kv_cache_dtype != "auto"