llama.cpp
f308ea70
- metal : tune soft_max number of threads (whisper/0)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
metal : tune soft_max number of threads (whisper/0)
References
#7281 - sync : ggml
Author
ggerganov
Committer
ggerganov
Parents
c3c88f29
Loading