]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix overflow in FA, tune performance (#14840)
authorJohannes Gäßler <redacted>
Wed, 23 Jul 2025 19:43:25 +0000 (21:43 +0200)
committerGitHub <redacted>
Wed, 23 Jul 2025 19:43:25 +0000 (21:43 +0200)
commita86f52b2859dae4db5a7a0bbc0f1ad9de6b43ec6
treebeda3832bfac5ffb66a1814af1dde89440d21f52
parentb284197df426fb189cdcfe56a43c863a788ac756
CUDA: fix overflow in FA, tune performance (#14840)
ggml/src/ggml-cuda/fattn-common.cuh
ggml/src/ggml-cuda/fattn-mma-f16.cuh
ggml/src/ggml-cuda/fattn-tile-f16.cu
ggml/src/ggml-cuda/fattn-tile-f32.cu
ggml/src/ggml-cuda/fattn-vec-f16.cuh
ggml/src/ggml-cuda/fattn-vec-f32.cuh
ggml/src/ggml-cuda/fattn-wmma-f16.cu
ggml/src/ggml-cuda/fattn.cu