GitLab

Putting the rocm symlink next to the runners is risky.  This moves
the payloads into a subdir to avoid potential clashes.

This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed.  It also cleans up after itself.

We now build only a single ROCm version (latest major) on both windows
and linux.  Given the large size of ROCms tensor files, we split the
dependency out.  It's bundled into the installer on windows, and a
separate download on windows.  The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.

For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us.  For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.

Signed-off-by: hishope <csqiye@126.com>

See https://reproducible-builds.org/ for why this is good.

This patch was done while working on reproducible builds for openSUSE.

Also fixes a few fit-and-finish items for better developer experience

Even though we weren't setting it to on, somewhere in the cmake config
it was getting toggled on.  By explicitly setting it to off, we get `/arch:AVX`
as intended.

This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.

This wires up some new logic to start using sysfs to discover AMD GPU
information and detects old cards we can't yet support so we can fallback to CPU mode.

Only apply patches if we have any, and make sure to cleanup
every file we patched at the end to leave the tree clean

* Fix clearing kv cache between requests with the same prompt

* fix powershell script

For old macs, accelerate seems to cause crashes, but for
AVX2 capable macs, it does not.

The linux build now support parallel CPU builds to speed things up.
This also exposes AMD GPU targets as an optional setting for advaced
users who want to alter our default set.

This also refines the build process for the ext_server build.

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.

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

This switches darwin to dynamic loading, and refactors the code now that no
static linking of the library is used on any platform

This reduces the built-in linux version to not use any vector extensions
which enables the resulting builds to run under Rosetta on MacOS in
Docker.  Then at runtime it checks for the actual CPU vector
extensions and loads the best CPU library available

In some cases we may want multiple variants for a given GPU type or CPU.
This adds logic to have an optional Variant which we can use to select
an optimal library, but also allows us to try multiple variants in case
some fail to load.

This can be useful for scenarios such as ROCm v5 vs v6 incompatibility
or potentially CPU features.

If the tree has a stale submodule, make sure we clean it up first