]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: fix crash with partial offloading of MoE (llama/13439)
authorJohannes Gäßler <redacted>
Sun, 11 May 2025 14:09:33 +0000 (16:09 +0200)
committerGeorgi Gerganov <redacted>
Tue, 13 May 2025 10:59:21 +0000 (13:59 +0300)
commit90b17a99bfd4ff0fbb047ca798f9b54e0fc78127
treeddab0a5b6f786299a7cfe14c4b0e80af452c9574
parente1b2ace0f8852b529cb23dee087aacad749a38b4
CUDA: fix crash with partial offloading of MoE (llama/13439)
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/mmq.cu
ggml/src/ggml-cuda/mmvq.cu