whisper.cpp/ggml
Tarek Dakhran 5e7ef7e4b0 ggml-cpu: fix SVE leftover path in ggml_vec_dot_f32 (llama/24699)
* ggml-cpu: fix SVE leftover path in ggml_vec_dot_f32

2D convolutions with kernel size 9 produced different results on SVE
enabled ARM devices. After debugging it turned out that ggml_vec_dot_f32
was using data from inactive lanes.

Use svmla_f32_m(pg, sum1, ax1, ay1) so inactive lanes retain sum1.

* cont : clean-up

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-06-26 16:03:57 +03:00
..
cmake ggml : Parallelize quant LUT init (llama/23595) 2026-05-25 12:26:07 +03:00
include sycl : support --split-mode tensor (llama/24152) 2026-06-26 16:03:57 +03:00
src ggml-cpu: fix SVE leftover path in ggml_vec_dot_f32 (llama/24699) 2026-06-26 16:03:57 +03:00
.gitignore whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
CMakeLists.txt hexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled weight repack, kernel-params, cached graphs (llama/24954) 2026-06-26 16:03:57 +03:00