]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama: offload output layer to GPU first (#18148)
authorJohannes Gäßler <redacted>
Thu, 18 Dec 2025 07:12:18 +0000 (08:12 +0100)
committerGitHub <redacted>
Thu, 18 Dec 2025 07:12:18 +0000 (08:12 +0100)
commit57c1e0564365b76a954304812cc90d3e60939bc7
tree951a1fd3c4cd35d9d9dc7725abde0b9f6638ea5f
parent9cff4cc5548113c1a1430c95e86cd3b348e3c063
llama: offload output layer to GPU first (#18148)
src/llama-model.cpp
src/llama.cpp