cturan/llama.cpp

mirror da https://github.com/cturan/llama.cpp

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