]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 07fbe19)
ggml : optimize cuda ssm_scan using warp-level reduction (#18505)
authorAadeshveer Singh <redacted>
Tue, 6 Jan 2026 18:24:34 +0000 (23:54 +0530)
committerGitHub <redacted>
Tue, 6 Jan 2026 18:24:34 +0000 (02:24 +0800)
commit24af22fc365ea6ef8e37875108a83658aa16fc8a
treeb64480c84629a69c444406b44935a352ebd1f199tree
parent07fbe19f1fbcfa09abca7cccc62eaf82c1567b7ecommit | diff
ggml : optimize cuda ssm_scan using warp-level reduction (#18505)

* ggml : optimize cuda ssm_scan using warp-level reduction

* ggml : apply code review suggestions (style, const, constexpr)

* ggml : add TODO regarding stride consistency
ggml/src/ggml-cuda/ssm-scan.cu diff | blob | history
Packaging of ggml-org/llama.cpp