]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/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 20:00:57 +0000 (22:00 +0200)
commitdbeb7916b8489bbe615907ad0a6d8f9eaf15f58e
tree531a90b92bf8e09b2cd2555f9d275bb82e43b0d0
parentfad2806352c58beca08667e30b2830c9ba192932
CUDA: fix Volta FlashAttention logic (llama/11615)
ggml/src/ggml-cuda/fattn-wmma-f16.cu
ggml/src/ggml-cuda/fattn.cu