git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	Diego Devesa <redacted>
	Mon, 25 Nov 2024 18:30:06 +0000 (19:30 +0100)
committer	GitHub <redacted>
	Mon, 25 Nov 2024 18:30:06 +0000 (19:30 +0100)
commit	10bce0450f0c4d80087e06312b9dbbab3e87f16b
tree	7eb8de91d8000b6c3f8ff9a9ce3d6600d8382914	tree
parent	1f922254f0c984a8fb9fbaa0c390d7ffae49aedb	commit \| diff

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

Packaging of ggml-org/llama.cpp

RSS Atom

common/arg.cpp		diff \| blob \| history
common/common.cpp		diff \| blob \| history
common/common.h		diff \| blob \| history
examples/server/server.cpp		diff \| blob \| history
examples/speculative-simple/speculative-simple.cpp		diff \| blob \| history
examples/speculative/speculative.cpp		diff \| blob \| history
ggml/src/ggml-backend-reg.cpp		diff \| blob \| history
include/llama.h		diff \| blob \| history
src/llama.cpp		diff \| blob \| history