llama.cpp

10bce045 - 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 (#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