0 0 0 C++

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

Diego Devesa committed 1y ago

10bce0450f0c4d80087e06312b9dbbab3e87f16b

Parent: 1f92225

Committed by GitHub <noreply@github.com> on 11/25/2024, 6:30:06 PM