mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-30 06:30:15 +01:00
1731d4238f
* add onednn * add sycl_f16 * add dnnl stream * add engine map * use dnnl for intel only * use fp16fp16fp16 * update doc |
||
---|---|---|
.. | ||
cmake | ||
include | ||
src | ||
.gitignore | ||
CMakeLists.txt |