xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-09 05:42:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improve multimodal hasher performance for re-used Image prompts (#22825)

Browse Source 
Signed-off-by: Staszek Pasko <staszek@gmail.com>
This commit is contained in:
Staszek Paśko 2025-08-15 14:32:56 +02:00 committed by GitHub
parent 49252cf59e
commit 22341b996e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
tests/multimodal/test_hasher.py
View File

@ -1,5 +1,6 @@
# SPDX-License-Identifier: Apache-2.0 # SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import uuid
from pathlib import Path from pathlib import Path
import numpy as np import numpy as np
@ -72,3 +73,22 @@ def test_hash_non_contiguous_array():
hasher = MultiModalHasher hasher = MultiModalHasher
# Both should be hashable and produce the same hashes # Both should be hashable and produce the same hashes
assert hasher.hash_kwargs(data=arr) == hasher.hash_kwargs(data=arr_c) assert hasher.hash_kwargs(data=arr) == hasher.hash_kwargs(data=arr_c)
def test_hash_image_exif_id():
# Test that EXIF ImageId tag can be used to store UUID
# and the hasher will use that instead of the image data.
image1 = image2 = Image.new("1", size=(10, 20))
id = uuid.uuid4()
image1.getexif()[Image.ExifTags.Base.ImageID] = id
image2 = Image.open(ASSETS_DIR / "image1.png")
image2.getexif()[Image.ExifTags.Base.ImageID] = "Not a UUID"
image2a = Image.open(ASSETS_DIR / "image1.png")
hasher = MultiModalHasher
# first image has UUID in ImageID, so it should hash to that UUID
assert hasher.hash_kwargs(image=image1) == hasher.hash_kwargs(
image=id.bytes)
# second image has non-UUID in ImageID, so it should hash to the image data
assert hasher.hash_kwargs(image=image2) == hasher.hash_kwargs(
image=image2a)

6
vllm/multimodal/hasher.py
View File

@ -2,6 +2,7 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import pickle import pickle
import uuid
from collections.abc import Iterable, Mapping from collections.abc import Iterable, Mapping
from typing import Union from typing import Union
@ -34,6 +35,11 @@ class MultiModalHasher:
return np.array(obj).tobytes() return np.array(obj).tobytes()
if isinstance(obj, Image.Image): if isinstance(obj, Image.Image):
exif = obj.getexif()
if Image.ExifTags.Base.ImageID in exif and isinstance(
exif[Image.ExifTags.Base.ImageID], uuid.UUID):
# If the image has exif ImageID tag, use that
return exif[Image.ExifTags.Base.ImageID].bytes
return cls.item_to_bytes( return cls.item_to_bytes(
"image", np.asarray(convert_image_mode(obj, "RGBA"))) "image", np.asarray(convert_image_mode(obj, "RGBA")))
if isinstance(obj, torch.Tensor): if isinstance(obj, torch.Tensor):