Skip to content

Conversation

@lukaszstolarczuk
Copy link
Contributor

and add verbose option to bench's integration tests.

"max",
batchSize=512,
slmNum=-1,
warmupIterations=2,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm not sure if we are interested in having scenarios with varying warmup iterations. I would go for one value that makes results variance minimal.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

heh, well, I was even planning on removing this param from Slm benchmark in CB repo 😉 thx!

@lukaszstolarczuk lukaszstolarczuk force-pushed the add-torch-slm-bench branch 2 times, most recently from 5e6ae8f to bbadbcb Compare December 18, 2025 13:14
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.

2 participants