]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama: fix magic number of 999 for GPU layers (#18266)
authorJohannes Gäßler <redacted>
Sat, 27 Dec 2025 19:18:35 +0000 (20:18 +0100)
committerGitHub <redacted>
Sat, 27 Dec 2025 19:18:35 +0000 (20:18 +0100)
commit026d2ad47247c006bd9ef6e583d76b6ab69875b6
tree13ad2065121bf3d5d0bde5a73555abda10dece77
parent06705fdcb3ef199d2c2c95a5e3cbb7cf9cc5256e
llama: fix magic number of 999 for GPU layers (#18266)

* llama: fix magic number of 999 for GPU layers

* use strings for -ngl, -ngld

* enacapsulate n_gpu_layers, split_mode
common/arg.cpp
common/common.cpp
common/common.h
include/llama.h
src/llama-context.cpp
src/llama-model.cpp
src/llama-model.h