git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-03-29 03:15:32 +02:00
Code Issues Packages Projects Releases Wiki Activity
50d5cecbda
llama.cpp/include
History
Diego Devesa 10bce0450f
llama : accept a list of devices to use to offload a model (#10497) 
* llama : accept a list of devices to use to offload a model

* accept `--dev none` to completely disable offloading

* fix dev list with dl backends

* rename env parameter to LLAMA_ARG_DEVICE for consistency
2024-11-25 19:30:06 +01:00
..
llama.h llama : accept a list of devices to use to offload a model (#10497) 2024-11-25 19:30:06 +01:00