GitLab

This commit introduces a more friendly way to build Ollama dependencies
and the binary without abusing `go generate` and removing the
unnecessary extra steps it brings with it.

This script also provides nicer feedback to the user about what is
happening during the build process.

At the end, it prints a helpful message to the user about what to do
next (e.g. run the new local Ollama).

update generate scripts with new `LLAMA_CUDA` variable, set `HIP_PLATFORM` to avoid compiler errors (#3528)

The subprocess change moved the build directory
arm64 builds weren't setting cross-compilation flags when building on x86

This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.

Flesh out our github actions CI so we can build official releaes.

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