]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f785fc9)
cuda : add warp-per-row wkv7 kernel for single-token decode (#26111)
author0 <redacted>
Tue, 11 Aug 2026 17:46:23 +0000 (01:46 +0800)
committerGitHub <redacted>
Tue, 11 Aug 2026 17:46:23 +0000 (20:46 +0300)
commit5988633170f66d71570275b89f5c78e0c236e67a
tree46187ad0896ec74c0bb1cd044d23b4e7063e7febtree
parentf785fc9ea485e6cfdda129978310aa52939c3619commit | diff
cuda : add warp-per-row wkv7 kernel for single-token decode (#26111)
ggml/src/ggml-cuda/wkv.cu diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp