]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
starcoder : add GPU offloading (#3827)
authorGeorgi Gerganov <redacted>
Sat, 28 Oct 2023 09:06:08 +0000 (12:06 +0300)
committerGitHub <redacted>
Sat, 28 Oct 2023 09:06:08 +0000 (12:06 +0300)
commitfdee152e4eebb78c191df0b074857111d7f2aba7
tree592d3c3cd7a1bdd3062682b7d1e49a6dde5491d1
parent41aee4df821854f37d90a45281f03b6db8d27de2
starcoder : add GPU offloading (#3827)

* starcoder : do not GPU split 1D bias tensors

* starcoder : offload layers to GPU

ggml-ci
llama.cpp