CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

kleidiai: add optimized per-channel kernels for Q8_0 (#16993)

Browse Source
This commit is contained in:
Charles Xu
2025-11-11 12:20:31 +01:00
committed by GitHub
parent 4a5b8aff40
commit 8c583242ad
4 changed files with 538 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-cpu/kleidiai/kernels.h
View File

@@ -87,3 +87,4 @@ struct ggml_kleidiai_kernels {
ggml_kleidiai_kernels * ggml_kleidiai_select_kernels(cpu_feature cpu_features, const ggml_tensor * tensor);
ggml_kleidiai_kernels * ggml_kleidiai_select_kernels_q4_0(cpu_feature features);
ggml_kleidiai_kernels * ggml_kleidiai_select_kernels_q8_0(cpu_feature features);