GitLab

Updated readme with the web link for haystack ollama integration

Let gpu.go and gen_linux.sh also find CUDA on Arch Linux

Refine the linux cuda/rocm developer docs

Add multiple CPU variants for Intel Mac

The runners are x86 so we can only run binaries that match.

This also refines the build process for the ext_server build.

fix: normalize name path before splitting

Bump llama.cpp to b1842 and add new cuda lib dep

Upstream llama.cpp has added a new dependency with the
NVIDIA CUDA Driver Libraries (libcuda.so) which is part of the
driver distribution, not the general cuda libraries, and is not
available as an archive, so we can not statically link it.  This may
introduce some additional compatibility challenges which we'll
need to keep an eye on.

Add macos cross-compile CI coverage

remove client.py

- prompt cache causes inferance to hang after some time

fix: request retry with error

improve cuda detection (rel. issue #1704)

Fix typo in arm mac arch script

Fix intel mac build

Make sure we're building an x86 ext_server lib when cross-compiling

remove double newlines in /set parameter

add max context length check

this fixes a subtle bug with makeRequestWithRetry where an HTTP status
error on a retried request will potentially not return the right err

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

After executing the `userdel ollama` command, I saw this message:

```sh
$ sudo userdel ollama
userdel: group ollama not removed because it has other members.
```

Which reminded me that I had to remove the dangling group too. For completeness, the uninstall instructions should do this too.

Thanks!

Fix up the CPU fallback selection

The memory changes and multi-variant change had some merge
glitches I missed.  This fixes them so we actually get the cpu llm lib
and best variant for the given system.