]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 77e3e4a)
llama : accept a list of devices to use to offload a model (llama/10497)
authorDiego Devesa <redacted>
Mon, 25 Nov 2024 18:30:06 +0000 (19:30 +0100)
committerGeorgi Gerganov <redacted>
Sun, 8 Dec 2024 18:14:35 +0000 (20:14 +0200)
commitac33379a35588ad7efd77c81b154380969588434
tree4a5562786d14a58b407e609449e229806f1f6b80tree
parent77e3e4a09051b4d6afa64e0430492e4df7f76f1ccommit | diff
llama : accept a list of devices to use to offload a model (llama/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
ggml/src/ggml-backend-reg.cpp diff | blob | history
Packaging of ggerganov/whisper.cpp