[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image bytes instead of pixel values (#29621)

Signed-off-by: Rahul Steiger <rasteiger@ethz.ch>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
ImaGoodFella
2025-12-02 21:49:02 +08:00
committed by GitHub
co-authored by Cyrus Leung
parent 68ffbca7e4
commit 60c3d413af
8 changed files with 95 additions and 19 deletions
+28
View File
@@ -2,12 +2,40 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from abc import ABC, abstractmethod
from dataclasses import dataclass
from pathlib import Path
from typing import Generic, TypeVar
import numpy as np
_T = TypeVar("_T")
@dataclass
class MediaWithBytes(Generic[_T]):
"""
Wrapper that couples a media object with its original encoded bytes.
This ensures the raw bytes and media object remain synchronized,
preventing cache corruption from in-place modifications.
The wrapper delegates attribute access to the underlying media object,
making it behave transparently like the wrapped type (e.g., PIL.Image).
"""
media: _T
original_bytes: bytes
def __array__(self, *args, **kwargs) -> np.ndarray:
"""Allow np.array(obj) to return np.array(obj.media)."""
return np.array(self.media, *args, **kwargs)
def __getattr__(self, name: str):
"""Delegate attribute access to the underlying media object."""
# This is only called when the attribute is not found on self
return getattr(self.media, name)
class MediaIO(ABC, Generic[_T]):
@abstractmethod
def load_bytes(self, data: bytes) -> _T: