]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 53f9250)
SYCL: Add mrope kernel (#13755)
authorAkarshan Biswas <redacted>
Fri, 30 May 2025 14:10:57 +0000 (19:40 +0530)
committerGitHub <redacted>
Fri, 30 May 2025 14:10:57 +0000 (19:40 +0530)
commitb49a8ff96b769b8a4c36d89fb783ec0135be582b
treec8fc09cf982b7b9b4621cefcacbf1b52098e0cc8tree
parent53f925074de02c5304b00c14b4d6d8910c58667dcommit | diff
SYCL: Add mrope kernel (#13755)

* SYCL: Add mrope kernel

* feat: Optimize rope operations with vectorization

Uses `sycl::vec` to load and store two elements at a time,
significantly improving performance in `rope_norm`,
`rope_neox`, and `rope_multi`. This reduces the number of memory
accesses and leverages SIMD instructions for faster execution.

* Use ceil_div
ggml/src/ggml-sycl/ggml-sycl.cpp diff | blob | history
ggml/src/ggml-sycl/rope.cpp diff | blob | history
Packaging of ggml-org/llama.cpp