]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: faster Deepseek FA, add Turing support (#13435)
authorJohannes Gäßler <redacted>
Wed, 14 May 2025 14:08:20 +0000 (16:08 +0200)
committerGitHub <redacted>
Wed, 14 May 2025 14:08:20 +0000 (16:08 +0200)
commit6da34fa27620fa56e3334172e023f4f2533df51f
treeab7b4b73c8700a666a34fab1d7f68226fb7dba7c
parent5e7d95e22e386d316f7f659b74c9c34b65507912
CUDA: faster Deepseek FA, add Turing support (#13435)
ggml/src/ggml-cuda/fattn-common.cuh
ggml/src/ggml-cuda/fattn-mma-f16.cuh
ggml/src/ggml-cuda/fattn.cu
ggml/src/ggml-cuda/ggml-cuda.cu