Skip to content

Fix PIL image cache key collisions across dimensions #9359

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
3em0 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix PIL image cache key collisions across dimensions #9359

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions swift/template/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -777,8 +777,8 @@ def prepare_generate_kwargs(self, generate_kwargs: Dict[str, Any], *, model=None

@staticmethod
def _save_pil_image(image: Image.Image) -> str:
img_bytes = image.tobytes()
img_hash = hashlib.sha256(img_bytes).hexdigest()
img_meta = f'{image.mode}:{image.width}:{image.height}:'.encode()
img_hash = hashlib.sha256(img_meta + image.tobytes()).hexdigest()
Comment on lines +780 to +781

@gemini-code-assist gemini-code-assist Bot May 16, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better memory efficiency, especially with large images, you can update the hash object incrementally instead of creating a new concatenated bytes object. This avoids allocating extra memory for the combined metadata and image bytes.

Suggested change
img_meta = f'{image.mode}:{image.width}:{image.height}:'.encode()
img_hash = hashlib.sha256(img_meta + image.tobytes()).hexdigest()
hasher = hashlib.sha256()
hasher.update(f'{image.mode}:{image.width}:{image.height}:'.encode())
hasher.update(image.tobytes())
img_hash = hasher.hexdigest()

tmp_dir = os.path.join(get_cache_dir(), 'tmp', 'images')
logger.info_once(f'create tmp_dir: {tmp_dir}')
os.makedirs(tmp_dir, exist_ok=True)
Expand Down
26 changes: 26 additions & 0 deletions tests/llm/test_template.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,14 @@
import os
import tempfile
import torch
import unittest
from unittest.mock import patch

from PIL import Image
from swift.infer_engine import RequestConfig, TransformersEngine
from swift.model import get_processor
from swift.template import get_template
from swift.template.base import Template
from swift.utils import get_logger, seed_everything

# os.environ['CUDA_VISIBLE_DEVICES'] = '0'
Expand Down Expand Up @@ -103,6 +107,28 @@ def test_tool_message_join(self):
f'{observation}tool2\n{observation}tool3\n')
assert res == ground_truth

def test_save_pil_image_uses_dimensions_in_cache_key(self):
width_a, height_a = 120, 80
width_b, height_b = 80, 120
self.assertEqual(width_a * height_a, width_b * height_b)

pixels = bytearray()
for i in range(width_a * height_a):
row = i // width_a
pixels.extend((255, 60, 60) if row % 10 < 5 else (60, 60, 255))
img_bytes = bytes(pixels)

image_a = Image.frombytes('RGB', (width_a, height_a), img_bytes)
image_b = Image.frombytes('RGB', (width_b, height_b), img_bytes)

with tempfile.TemporaryDirectory() as cache_dir, patch('swift.template.base.get_cache_dir', return_value=cache_dir):
path_a = Template._save_pil_image(image_a)
path_b = Template._save_pil_image(image_b)

self.assertNotEqual(path_a, path_b)
self.assertEqual(Image.open(path_a).size, (width_a, height_a))
self.assertEqual(Image.open(path_b).size, (width_b, height_b))


if __name__ == '__main__':
unittest.main()