]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml : optimize cuda ssm_scan using warp-level reduction (llama/18505)
authorAadeshveer Singh <redacted>
Tue, 6 Jan 2026 18:24:34 +0000 (23:54 +0530)
committerGeorgi Gerganov <redacted>
Sun, 11 Jan 2026 09:02:08 +0000 (11:02 +0200)
commit4c540d0b4e9d2f1f24e82c5bf05427fc1d6ecacb
tree7e0a164f7ae6a30049b3a422308e1dc91707a948
parent39b43fdf15c13f4afad04f9d870cadbfadc980b3
ggml : optimize cuda ssm_scan using warp-level reduction (llama/18505)

* ggml : optimize cuda ssm_scan using warp-level reduction

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

* ggml : add TODO regarding stride consistency
src/ggml-cuda/ssm-scan.cu