]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: fix --split-mode row for MMQ (llama/13323)
authorJohannes Gäßler <redacted>
Tue, 6 May 2025 06:36:46 +0000 (08:36 +0200)
committerGeorgi Gerganov <redacted>
Wed, 7 May 2025 14:44:35 +0000 (17:44 +0300)
commit312bc0eaeed7d98777fb7de29b2b237e5a725fc6
treeb5b940a60c523441ed11da7c3efdec0463c7feb0
parent31e199b2fb8173c35e1b6ef50393fec4a9d43abe
CUDA: fix --split-mode row for MMQ (llama/13323)
src/ggml-cuda/mmq.cu
src/ggml-cuda/mmq.cuh