]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 6f1b636)
CUDA: add FP32 FlashAttention vector kernel (#7188)
authorJohannes Gäßler <redacted>
Sun, 12 May 2024 17:40:45 +0000 (19:40 +0200)
committerGitHub <redacted>
Sun, 12 May 2024 17:40:45 +0000 (19:40 +0200)
commitdc685be46622a8fabfd57cfa804237c8f15679b8
tree43b1baf9bb0ab8d39e68f0e865a34fad37a59370tree
parent6f1b63606fc68a09d62d1d74dbd156c35219026dcommit | diff
CUDA: add FP32 FlashAttention vector kernel (#7188)

* CUDA: add FP32 FlashAttention vector kernel

* fixup! CUDA: add FP32 FlashAttention vector kernel

* fixup! fixup! CUDA: add FP32 FlashAttention vector kernel

* fixup! fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
ggml-cuda.cu diff | blob | history
ggml-cuda/common.cuh diff | blob | history
ggml-cuda/fattn-common.cuh [new file with mode: 0644] blob
ggml-cuda/fattn-vec-f16.cu [new file with mode: 0644] blob
ggml-cuda/fattn-vec-f16.cuh [new file with mode: 0644] blob
ggml-cuda/fattn-vec-f32.cu [new file with mode: 0644] blob
ggml-cuda/fattn-vec-f32.cuh [new file with mode: 0644] blob
ggml-cuda/fattn.cu diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp