]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 5126c41)
CUDA: disable cuda graph when using n-cpu-moe (#18593)
authorAman Gupta <redacted>
Sun, 4 Jan 2026 17:37:48 +0000 (01:37 +0800)
committerGitHub <redacted>
Sun, 4 Jan 2026 17:37:48 +0000 (01:37 +0800)
commit908a9e5a1eaaff345f05087beafdf43d31e3f00a
treead18de82a3fe4368d5aadd97530891bf6dfc2809tree
parent5126c41c1cae810a28e89dd424f729ef59417341commit | diff
CUDA: disable cuda graph when using n-cpu-moe (#18593)

* CUDA: disable cuda graph when using n-cpu-moe

* call ggml_cuda_set_device
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp