]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: fix Volta FlashAttention logic (llama/11615)
authorJohannes Gäßler <redacted>
Mon, 3 Feb 2025 12:25:56 +0000 (13:25 +0100)
committerGeorgi Gerganov <redacted>
Mon, 3 Feb 2025 12:44:49 +0000 (14:44 +0200)
commitaf8e7e15fa0b97444e1631711fe0ca16f7d168ef
treef65413bb6b6010fe01a37ad3dbdf584d4b58d4d7
parent71678e11ec35742d70c5c39bdd8e7156f1b2d6b8
CUDA: fix Volta FlashAttention logic (llama/11615)
src/ggml-cuda/fattn-wmma-f16.cu
src/ggml-cuda/fattn.cu