]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 66c9206)
ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (#13882)
authorVineel Abhinav <redacted>
Thu, 29 May 2025 09:18:43 +0000 (14:48 +0530)
committerGitHub <redacted>
Thu, 29 May 2025 09:18:43 +0000 (12:18 +0300)
commitdd8ba93416f492c168f7e20f0b1434c08ebeaeb5
tree689f063beabc00f70ec7886e75d4040ab71bc028tree
parent66c92061f5c34d2f9a630b7b50cca5ce3ebb4b16commit | diff
ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (#13882)

* F32-Mamba-Seq_Scan-SVE

* Fix formatting

* ggml : missing space

---------

Co-authored-by: Georgi Gerganov <redacted>
ggml/src/ggml-cpu/ops.cpp diff | blob | history
ggml/src/ggml-cpu/vec.h diff | blob | history
Packaging of ggml-org/llama.cpp