]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix crash with partial offloading of MoE (#13439)
authorJohannes Gäßler <redacted>
Sun, 11 May 2025 14:09:33 +0000 (16:09 +0200)
committerGitHub <redacted>
Sun, 11 May 2025 14:09:33 +0000 (16:09 +0200)
commit7474e00b34629e9cd8b06bc87ad935584ea30f8e
tree6340acb2ce8abc5c906b8e83fa41f513662a8eda
parent7f323a589f8684c0eb722e7309074cb5eac0c8b5
CUDA: fix crash with partial offloading of MoE (#13439)
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/mmq.cu
ggml/src/ggml-cuda/mmvq.cu