]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA GPU acceleration for LoRAs + f16 models (#1970)
authorJohannes Gäßler <redacted>
Wed, 28 Jun 2023 16:35:54 +0000 (18:35 +0200)
committerGitHub <redacted>
Wed, 28 Jun 2023 16:35:54 +0000 (18:35 +0200)
commit7f9753fa1263c4eded9a3de19778562f0e1093d7
treed003fd220c810884cf93ed17d0f4ae518d0bf3e2
parentcfa0750bc9dbc2d957a91b8ed09ab0035d8f3d4e
CUDA GPU acceleration for LoRAs + f16 models (#1970)
examples/common.cpp
ggml-cuda.cu
ggml-cuda.h
llama.cpp