]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: afbbfaa)
ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels (#9217)
authorCharles Xu <redacted>
Wed, 25 Sep 2024 13:12:20 +0000 (15:12 +0200)
committerGitHub <redacted>
Wed, 25 Sep 2024 13:12:20 +0000 (16:12 +0300)
commit1e436302188a704ac9ea044af03193648806f19c
treeb4bb842b03e2007319053602f42239a0955842fctree
parentafbbfaa537a96f562c34df4542930fa951b40d9ecommit | diff
ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels (#9217)

* ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels

* added fallback mechanism when the offline re-quantized model is not
optimized for the underlying target.

* fix for build errors

* remove prints from the low-level code

* Rebase to the latest upstream
ggml/src/ggml-aarch64.c diff | blob | history
Packaging of ggml-org/llama.cpp