]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3e684f2)
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 19:05:46 +0000 (21:05 +0200)
commita81fbfc78ec74aae77a29156b6290e3329aa1d90
tree1e14bf9a63ed0cdcc9dc8ccb3624db608c01e08dtree
parent3e684f26c1651c8d4b02cd97503b3fb4e303c507commit | 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
ggml/src/ggml-cpu/repack.cpp diff | blob | history
Packaging of ggerganov/whisper.cpp