-
-
Notifications
You must be signed in to change notification settings - Fork 5k
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
[Misc] Log spec decode metrics #6454
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Full CI run is still required to merge this PR so once the PR is ready to go, please make sure to run it. If you need all test signals in between PR commits, you can trigger full CI as well. To run full CI, you can do one of these:
🚀 |
/ready |
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.
thanks so much for adding this
CI blocked by #6453. Will rebase once it merged. |
8b67a8b
to
5680452
Compare
Signed-off-by: Alvant <[email protected]>
This PR adds speculative decoding metrics to engine metrics so that they can be dumped and evaluated. Two unit tests were added accordingly:
test_metrics.py
, added a unit test to verify theres metrics are correctly logged.cc @cadedaniel @alexm-neuralmagic