-
-
Notifications
You must be signed in to change notification settings - Fork 6.3k
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.
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
[V1][Bugfix] Skip hashing empty or None mm_data #11386
Conversation
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I guess it's because mm hasher was just turned on by default since 2 days ago.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ah sorry I should have caught this, thanks for the fix!
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Signed-off-by: Bowen Wang <abmfy@icloud.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
prompt["multi_modal_data"]
can be None or an empty dict. In such a case, vLLM currently errors at thehash_prompt_mm_data
method. This PR fixes the bug.I met this bug when running
benchmark_throughput.py
. Not sure why this was not detected in earlier PRs.