]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: skip masked KV slices for all FA kernels (llama/14924)
authorJohannes Gäßler <redacted>
Wed, 30 Jul 2025 13:46:13 +0000 (15:46 +0200)
committerGeorgi Gerganov <redacted>
Sat, 2 Aug 2025 14:51:21 +0000 (17:51 +0300)
commita42bdfd2fdb854633540d2d34453c383679de352
treeb560ec63d952e7754703319edee4da9b95c873bc
parent3053e050bdc7878d9a11f9065abf010e18ce403f
CUDA: skip masked KV slices for all FA kernels (llama/14924)
src/ggml-cuda/common.cuh
src/ggml-cuda/fattn-common.cuh
src/ggml-cuda/fattn-mma-f16.cuh
src/ggml-cuda/fattn-tile-f16.cu
src/ggml-cuda/fattn-tile-f32.cu
src/ggml-cuda/fattn-vec-f16.cuh
src/ggml-cuda/fattn-vec-f32.cuh
src/ggml-cuda/fattn-wmma-f16.cu
src/ggml-cuda/fattn.cu