]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 52cf111)
ggml-cpu: handle 3d tensors in repack mat_mul (#17030)
authorAlberto Cabrera Pérez <redacted>
Wed, 12 Nov 2025 12:52:19 +0000 (12:52 +0000)
committerGitHub <redacted>
Wed, 12 Nov 2025 12:52:19 +0000 (14:52 +0200)
commit1c398dc9eca9c366ce98deb0e6f3538e444ebc8a
treef7bf5845d51f9612ceae467d2c347143e6b0de47tree
parent52cf111b312d6747fd553782bee7f9fc808bf564commit | diff
ggml-cpu: handle 3d tensors in repack mat_mul (#17030)

* ggml-cpu: handle 3d tensors in repack mul_mat

* Removed unnecessary branch, removed need for <algorithm>

* Fixed dst_ptr pointer in chunk + clang_format

* GGML_ASSERT to check wdata within bounds

* Accidental ggml.h inclusion

* Improved GGML_ASSERT on wdata boundaries
ggml/src/ggml-cpu/repack.cpp diff | blob | history
Packaging of ggml-org/llama.cpp