mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-30 08:10:20 +00:00
0cb7a0683b
* opencl: add mm_q8_0_f32 * opencl: fix data loading for incomplete tile * opencl: use q8_0 mm for larger matrix * opencl: add some tests to cover the path