CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity
854 Commits 496 Branches 4,675 Tags
652c849643a81d0fee3f178b90f093f71d1f49f5
Commit Graph

3 Commits

Author SHA1 Message Date
Georgi Gerganov
652c849643 ggml : add is_ram_shared to ggml_backend 
Metal can share the RAM memory and can utilize mmap without temp buffer
 2023-07-18 18:51:02 +03:00
Georgi Gerganov
90503f150d llama : init metal backend as CPU backend for now 2023-07-18 17:54:16 +03:00
slaren
0d2b66c638 ggml backend interface wip 
refactor ggml-cuda
 2023-07-16 14:56:46 +02:00