cturan/llama.cpp

miroir de https://github.com/cturan/llama.cpp

Auteur	SHA1 Message	Date
Georgi Gerganov	16bcc1259d kv-cache : pad the cache size to 256 for performance (#17046)	il y a 2 mois
Johannes Gäßler	e81b8e4b7f llama: use FA + max. GPU layers by default (#15434)	il y a 4 mois
Georgi Gerganov	d2fcd91cf9 server : disable context shift by default (#15416)	il y a 5 mois
Diego Devesa	1d36b3670b llama : move end-user examples to tools directory (#13249)	il y a 8 mois