whisper.cpp
eebf6bc0
- ggml-cpu: faster AVX2 variant for IQ1_M (llama/12216)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
320 days ago
ggml-cpu: faster AVX2 variant for IQ1_M (llama/12216)
References
#2868 - sync : ggml
Author
remyoudompheng
Committer
ggerganov
Parents
dc8f423b
Loading
