llama.cpp
98311c42 - llama : make quantize example up to 2.7x faster (#3115)

Commit

2 years ago

llama : make quantize example up to 2.7x faster (#3115)

References

#3115 - llama : make quantize example up to 2.7x faster

Author

cebtenzzre

cebtenzzre

Parents

Loading