Re: llama.cpp, whisper.cpp, ggml: Next steps

[Petter Reinholdtsen <pere@hungry.com>]

[Petter Reinholdtsen]
> I managed to get the whisper.cpp git repo on salsa to build with the
> non-embedded ggml package.  Please have a look at
> <URL: https://salsa.debian.org/deeplearning-team/whisper.cpp >.

I forgot to mention I had to adjust the ggml build slightly, to include
the ggml-cpp.h file.  Patch sent upstream as
<URL: https://github.com/ggml-org/ggml/pull/1126 >.

Note, to get the programs in the whisper.cpp package working, one need
to se LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/ggml/ or similar.  I
have not been able to get cmake to install a rpath/runpath into the
binaries.

-- 
Happy hacking
Petter Reinholdtsen