]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 189d684)
ggml-cuda : support stablelm rope (#4156)
authorslaren <redacted>
Fri, 24 Nov 2023 17:04:31 +0000 (18:04 +0100)
committerGitHub <redacted>
Fri, 24 Nov 2023 17:04:31 +0000 (18:04 +0100)
commit8a052c131ed3525313cdb84e5ae4e2b6cf8d2e24
tree4c7f2e9a5929ac9db83c36a2cab588f3112798dftree
parent189d68446e7ef21e8f3af3c0a3d91c35a39aec89commit | diff
ggml-cuda : support stablelm rope (#4156)

* ggml-cuda : support stablelm rope

* remove unused freq_base kernel parameter

* add n_dims parameter to llm_build_k_shift, default to n_rot via overload

* llama : fix llm_build_k_shift args

---------

Co-authored-by: Georgi Gerganov <redacted>
ggml-cuda.cu diff | blob | history
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp