-
Notifications
You must be signed in to change notification settings - Fork 3.9k
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
When running on ARM big.LITTLE architecture, more threads = slower execution #1248
Labels
bug
Something isn't working
Comments
ggerganov
pushed a commit
that referenced
this issue
Sep 6, 2023
jacobwu-b
pushed a commit
to jacobwu-b/Transcriptify-by-whisper.cpp
that referenced
this issue
Oct 24, 2023
jacobwu-b
pushed a commit
to jacobwu-b/Transcriptify-by-whisper.cpp
that referenced
this issue
Oct 24, 2023
vonstring
pushed a commit
to vonstring/whisper.cpp
that referenced
this issue
Nov 7, 2023
landtanin
pushed a commit
to landtanin/whisper.cpp
that referenced
this issue
Dec 16, 2023
ryanrapp
pushed a commit
to ryanrapp/attentional-ios
that referenced
this issue
Jan 9, 2024
iThalay
pushed a commit
to iThalay/whisper.cpp
that referenced
this issue
Sep 23, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Whisper.cpp seems reliant on max-frequency or is otherwise exhibiting some sort of synchronous behavior when operating multiple threads that can cause overall performance to worsen substantially when using more threads on a big.LITTLE architecture.
This may just be how the algorithm works, but I still wanted to log the issue to document it.
Further details:
The text was updated successfully, but these errors were encountered: