llama.cpp
bcfebf24 - metal : add F32 -> Q8_0 copy kernel

Login via GitHub
Home
Pricing
FAQ
Install

Login via GitHub

Commit

2 years ago

metal : add F32 -> Q8_0 copy kernel

References

#4312 - llama : support quantum K cache

Author

ggerganov

ggerganov

Parents

FAQ Terms Privacy Refunds Impressum

Loading