Skip to content

[V0][Bugfix] Fix Mamba cache crashing #15296

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
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[V0][Bugfix] Fix Mamba cache crashing #15296

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4a8e39f
fix mamba crash due to finished req ids handling
benchislett Mar 21, 2025
99995b0
Merge branch 'main' into patch-mamba-cache-slots
benchislett Apr 11, 2025
4a90934
Merge branch 'main' into patch-mamba-cache-slots
benchislett May 29, 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
8 changes: 6 additions & 2 deletions vllm/engine/llm_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1339,8 +1339,12 @@ def step(self) -> List[Union[RequestOutput, PoolingRequestOutput]]:
ctx.seq_group_metadata_list = seq_group_metadata_list
ctx.scheduler_outputs = scheduler_outputs

finished_requests_ids = self.scheduler[
virtual_engine].get_and_reset_finished_requests_ids()
if scheduler_outputs.is_empty():
finished_requests_ids = []
else:
finished_requests_ids = self.scheduler[
virtual_engine].get_and_reset_finished_requests_ids()

# When n>1, elements in self.seq_id_to_seq_group should be deleted
# here, otherwise memory leaks.
for finished_request_id in finished_requests_ids:
Expand Down