Why is chunked-prefill-size divided by dp^2? #11193
Unanswered
GaGa55555LaLa
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
When we are doing offline_benchmark_throughput on deepseek-r1 model, we enable dp attention, then chunked-prefill-size would be divided by dp^2.
Why?
Beta Was this translation helpful? Give feedback.
All reactions