Skip to content

[Bugfix] Multi-modal caches not acting like LRU caches #16593

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

Merged
merged 4 commits into from
Apr 14, 2025
Merged

[Bugfix] Multi-modal caches not acting like LRU caches #16593

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a906993
[Bugfix] Multi-modal caches not acting like LRU caches
DarkLight1337 Apr 14, 2025
8420d58
Update cache and tests
DarkLight1337 Apr 14, 2025
8108c36
Try fix pre-commit
DarkLight1337 Apr 14, 2025
931d094
Fix
DarkLight1337 Apr 14, 2025
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
5 changes: 3 additions & 2 deletions vllm/v1/engine/mm_input_cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ def get_and_update_p0(

full_mm_inputs = list[Optional[MultiModalKwargs]]()
for mm_input, mm_hash in zip(mm_inputs, mm_hashes):
if mm_hash in self.mm_cache:
if self.mm_cache.get(mm_hash) is not None:
mm_input = None
else:
self.mm_cache[mm_hash] = mm_input
Expand All @@ -73,7 +73,8 @@ def get_and_update_p1(
full_mm_inputs = list[MultiModalKwargs]()
for mm_input, mm_hash in zip(mm_inputs, mm_hashes):
if mm_input is None:
mm_input = self.mm_cache[mm_hash]
mm_input = self.mm_cache.get(mm_hash)
assert mm_input is not None, f"Missing {mm_hash=}"
else:
self.mm_cache[mm_hash] = mm_input

Expand Down