]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: launch_bounds, small q4_K, q5_K mmq refactor (#2596)
authorJohannes Gäßler <redacted>
Mon, 14 Aug 2023 08:41:22 +0000 (10:41 +0200)
committerGitHub <redacted>
Mon, 14 Aug 2023 08:41:22 +0000 (10:41 +0200)
commit1cd06fa25eb859b14b3427a1d815a48f25fc3c34
tree948984bc42eeb38eb09344fb0744af0621cd794c
parent2feb8934eb75ca63f3c42724229cce1df9579c8e
CUDA: launch_bounds, small q4_K, q5_K mmq refactor (#2596)
ggml-cuda.cu