mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 10:54:36 +00:00
5cb6209de5
- cmake has a hardcoded `onemkl` that will cause linker failure for AMD path and needs to be changed - docfix: oneMKL compile needs `-DHIP_TARGETS` not `-DHIPTARGETS` - docfix: modified cmake build parameters to pass in more linker flags, otherwise linking will fail (might be slight overkill, but without adding `-DCMAKE_SHARED_LINKER_FLAGS` it fails |
||
---|---|---|
.. | ||
backend | ||
development | ||
android.md | ||
build.md | ||
docker.md | ||
install.md |