This commit aims to provide the Ollama maintainers with maximum control
of the distribution build process by creating a cross-platform shim.
Currently, we have no flexibility, or control of the process (pre and
post) or even the quality of the build.
By introducing a shim, and propagating it out to Homebrew, et al., we
can soon after ensure that the build process is consistent, and
reliable.
This also happens to remove the requirement for go generate and the
build tag hacks, but it does still support go generate in the flow, at
least until we can remove it after the major distribution use the new
build process.
About the script:
Beyond giving the Ollama maintainers drastically more control over the
build process, the script also provides a few other benefits:
- It is cross-platform, and can be run on any platform that supports Go
(a hard requirement for building Ollama anyway).
- It can can check for correct versions of cmake, and other dependencies
before starting the build process, and provide helpful error messages
to the user if they are not met.
- It can be used to build the distribution for any platform,
architecture, or build type (debug, release, etc.) with a single
command. Currently, it is two commands.
- It can skip parts of the build process if they are already done, such
as build the C dependencies. Of course there is a -f flag to force
rebuild.
- So much more!
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).
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.
