]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 673cfef)
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064)
authorPrashant Vithule <redacted>
Fri, 28 Feb 2025 07:36:12 +0000 (13:06 +0530)
committerGitHub <redacted>
Fri, 28 Feb 2025 07:36:12 +0000 (09:36 +0200)
commit05e6f5aad0a4bb48fb2775f2a78505540fdbc47d
treec2f92c0461f1246e24632456707135983df5b32ctree
parent673cfef9aa8daad09966208909f346eb996628a4commit | diff
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064)

* Added SVE Support for Q2_K Quantized Models

* Use 4-space indentation in the switch cases

* removed comments lines

* Remove the loop Retain the curly bracess for better understanding of code

* Remove the comment like added for q3_k_q8_k kernel

---------

Co-authored-by: vithulep <redacted>
ggml/src/ggml-cpu/ggml-cpu-quants.c diff | blob | history
Packaging of ggml-org/llama.cpp