]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a410713)
cuda : concat implementation for quantized types (#25303)
authorfairydreaming <redacted>
Sun, 5 Jul 2026 15:26:24 +0000 (17:26 +0200)
committerGitHub <redacted>
Sun, 5 Jul 2026 15:26:24 +0000 (23:26 +0800)
commit78d2f524682d9fee790a6460c93d018dafeb5229
tree80d40fce7910c272c6a2e1dcf402e9a06f8ee8c1tree
parenta4107133a634250c8c9d888bc0bc8520dcfd6105commit | diff
cuda : concat implementation for quantized types (#25303)

* cuda : concat implementation for quantized types

* chore : apply am17an clever suggestion to shorten the code

---------

Co-authored-by: Stanisław Szymczyk <redacted>
ggml/src/ggml-cuda/concat.cu diff | blob | history
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp