]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : mark LLM_ARCH_STARCODER as full offload supported (#3945)
authorMeng Zhang <redacted>
Sun, 5 Nov 2023 12:40:08 +0000 (04:40 -0800)
committerGitHub <redacted>
Sun, 5 Nov 2023 12:40:08 +0000 (14:40 +0200)
commit3d48f42efcd05381221654376e9f6f69d76af739
tree56ea096ffb23eb86e66a97ac04faccefb4e63b3b
parentc41ea36eaa3548776de4cb3d5d49b925cd3fc0f2
llama : mark LLM_ARCH_STARCODER as full offload supported (#3945)

as done in https://github.com/ggerganov/llama.cpp/pull/3827
llama.cpp