GitLab

This should resolve the problem where we don't fully unload from the GPU
when we go idle.

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 reverts commit 6920964b.

This reverts commit 2f9ed52b.

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.

Make sure that when a shutdown signal comes, we shutdown quickly instead
of waiting for a potentially long exchange to wrap up.

When we store our libraries in a temp dir, a reaper might clean
them when we are idle, so make sure to check for them before
we reload.

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

This requires an upstream change to support graceful termination,
carried as a patch.

* 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.

This wires up logging in llama.cpp to always go to stderr, and also
turns up logging if OLLAMA_DEBUG is set.

Detect potential error scenarios so we can fallback to CPU mode without
hitting asserts.

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.