Skip to content

Conversation

joerunde
Copy link
Collaborator

@joerunde joerunde commented Oct 8, 2025

Description

Following up on #509, this fixes up a few remaining tests that were setting their own max model lengths instead of using the default. Using the default makes it much easier to respond to changes in hardware support

Signed-off-by: Joe Runde <joe@joerun.de>
Copy link

github-actions bot commented Oct 8, 2025

👋 Hi! Thank you for contributing to vLLM support on Spyre.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, first install the linting requirements, then run format.sh and commit the changes. This can be done with uv directly:

uv sync --frozen --group lint --active --inexact

Or this can be done with pip:

uv pip compile --group lint > requirements-lint.txt
pip install -r requirements-lint.txt
bash format.sh

Now you are good to go 🚀

@wallashss
Copy link
Collaborator

LPGTM

@jberkhahn
Copy link
Collaborator

i like defaults, even if they use horrible monkeypatching

@joerunde
Copy link
Collaborator Author

joerunde commented Oct 8, 2025

Technically most of these aren't monkeypatching, they're just using pytest parameterization!

@joerunde joerunde merged commit 642bbce into main Oct 8, 2025
19 checks passed
@joerunde joerunde deleted the more-512-tokens branch October 8, 2025 21:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants