]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
overview / pkg / ggml / sources / ggml / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f45db47)
ggml-cpu: handle 3d tensors in repack mat_mul (llama/17241)
authorAlberto Cabrera Pérez <redacted>
Thu, 13 Nov 2025 20:53:00 +0000 (20:53 +0000)
committerGeorgi Gerganov <redacted>
Mon, 17 Nov 2025 13:34:43 +0000 (15:34 +0200)
commit2a8303b88e03c66a6807a2d296a985b7ef19f9e0
tree9493a616b457ceeb7fb0cd783d85581bffb20e9atree
parentf45db4747f1d15b75a96443ee97a0aa5c6b21196commit | diff
ggml-cpu: handle 3d tensors in repack mat_mul (llama/17241)

* 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

* Address performance regression in Qwen and llama.cpp due to chunking
src/ggml-cpu/repack.cpp diff | blob | history
Packaging of ggml-org/ggml