]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix crash on large batch size for MoE models (#13384)
authorJohannes Gäßler <redacted>
Fri, 9 May 2025 10:14:04 +0000 (12:14 +0200)
committerGitHub <redacted>
Fri, 9 May 2025 10:14:04 +0000 (12:14 +0200)
commit5c86c9ed3ef1cc7307fdce05f0f0e2e45253cf90
tree3242daaf24eb4050e133fcb8f1dbf78ea3882936
parentefb8b47eda78ea8ae570d4fece3953aae499289e
CUDA: fix crash on large batch size for MoE models (#13384)
ggml/src/ggml-cuda/getrows.cu